机器学习学术速递[11.12]

cs.LG 方向，今日共计87篇

Graph相关(图学习|图神经网络|图优化等)(7篇)

【1】 Poisoning Knowledge Graph Embeddings via Relation Inference Patterns 标题：通过关系推理模式毒化知识图嵌入 链接：https://arxiv.org/abs/2111.06345

作者：Peru Bhardwaj,John Kelleher,Luca Costabello,Declan O'Sullivan 机构：Declan O’Sullivan,∗, ADAPT Centre, Trinity College Dublin, Ireland, ADAPT Centre, TU Dublin, Ireland, Accenture Labs, Ireland 备注：Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) 摘要：针对知识图中的链接预测任务，研究了针对知识图嵌入（KGE）模型生成数据中毒攻击的问题。为了毒害KGE模型，我们建议利用它们的归纳能力，这些归纳能力是通过知识图中的对称、反转和组合等关系模式捕获的。具体来说，为了降低模型对目标事实的预测置信度，我们建议提高模型对一组诱饵事实的预测置信度。因此，我们通过不同的推理模式设计对抗性添加，以提高模型对诱饵事实的预测可信度。我们的实验表明，对于两个公开可用的数据集，在四个KGE模型上，提出的中毒攻击优于最新的基线。我们还发现，基于对称模式的攻击可以推广到所有模型数据集组合，这表明KGE模型对这种模式的敏感性。 摘要：We study the problem of generating data poisoning attacks against Knowledge Graph Embedding (KGE) models for the task of link prediction in knowledge graphs. To poison KGE models, we propose to exploit their inductive abilities which are captured through the relationship patterns like symmetry, inversion and composition in the knowledge graph. Specifically, to degrade the model's prediction confidence on target facts, we propose to improve the model's prediction confidence on a set of decoy facts. Thus, we craft adversarial additions that can improve the model's prediction confidence on decoy facts through different inference patterns. Our experiments demonstrate that the proposed poisoning attacks outperform state-of-art baselines on four KGE models for two publicly available datasets. We also find that the symmetry pattern based attacks generalize across all model-dataset combinations which indicates the sensitivity of KGE models to this pattern.

【2】 Implicit SVD for Graph Representation Learning 标题：用于图表示学习的隐式奇异值分解 链接：https://arxiv.org/abs/2111.06312

作者：Sami Abu-El-Haija,Hesham Mostafa,Marcel Nassar,Valentino Crespi,Greg Ver Steeg,Aram Galstyan 机构：USC Information Sciences Institute, Intel Labs 备注：None 摘要：用于图形表征学习（GRL）的最新方法（SOTA）的性能最近有所改进，但其代价是训练所需的大量计算资源，例如，在许多数据时代通过backprop计算梯度。同时，奇异值分解（SVD）可以找到凸问题的闭式解，只需使用几个阶段。在本文中，我们使GRL在计算上更易于处理，适用于那些具有普通硬件的系统。我们设计了一个计算\textit{隐式}定义矩阵SVD的框架，并将该框架应用于几个GRL任务。对于每个任务，我们推导SOTA模型的线性近似，在这里我们设计（存储成本高昂）矩阵$\mathbf{M}$，并通过$\mathbf{M}$的SVD以封闭形式训练模型，而不计算$\mathbf{M}$的条目。通过在一个步骤中收敛到一个唯一点，并且不计算梯度，我们的模型显示了在各种图表（如文章引用和生物相互作用网络）上具有竞争力的经验测试性能。更重要的是，SVD可以初始化更深层次的模型，该模型几乎在任何地方都是非线性的，尽管当其参数位于SVD初始化的超平面上时，它的行为是线性的。更深层次的模型可以在几个时期内进行微调。总的来说，我们的程序训练速度比最先进的方法快数百倍，同时在经验测试性能上竞争。我们在以下位置开放了我们的实现：https://github.com/samihaija/isvd 摘要：Recent improvements in the performance of state-of-the-art (SOTA) methods for Graph Representational Learning (GRL) have come at the cost of significant computational resource requirements for training, e.g., for calculating gradients via backprop over many data epochs. Meanwhile, Singular Value Decomposition (SVD) can find closed-form solutions to convex problems, using merely a handful of epochs. In this paper, we make GRL more computationally tractable for those with modest hardware. We design a framework that computes SVD of \textit{implicitly} defined matrices, and apply this framework to several GRL tasks. For each task, we derive linear approximation of a SOTA model, where we design (expensive-to-store) matrix $\mathbf{M}$ and train the model, in closed-form, via SVD of $\mathbf{M}$, without calculating entries of $\mathbf{M}$. By converging to a unique point in one step, and without calculating gradients, our models show competitive empirical test performance over various graphs such as article citation and biological interaction networks. More importantly, SVD can initialize a deeper model, that is architected to be non-linear almost everywhere, though behaves linearly when its parameters reside on a hyperplane, onto which SVD initializes. The deeper model can then be fine-tuned within only a few epochs. Overall, our procedure trains hundreds of times faster than state-of-the-art methods, while competing on empirical test performance. We open-source our implementation at: https://github.com/samihaija/isvd

【3】 DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks 标题：DropGNN：随机丢弃提高了图神经网络的表达能力 链接：https://arxiv.org/abs/2111.06283

作者：Pál András Papp,Karolis Martinkus,Lukas Faber,Roger Wattenhofer 机构：ETH Zurich 备注：Published in the 35th Conference on Neural Information Processing Systems (NeurIPS 2021) 摘要：本文研究了辍学图神经网络（DropGNNs），这是一种旨在克服标准GNN框架局限性的新方法。在DropGNNs中，我们在输入图上执行多个GNN运行，其中一些节点在每个运行中随机独立地被丢弃。然后，我们结合这些运行的结果来获得最终结果。我们证明了DropGNNs可以区分不同的图邻域，这些图邻域不能被消息传递的GNNs分开。我们推导了确保可靠的辍学分布所需的运行次数的理论界，并证明了关于辍学的表达能力和限制的若干性质。我们通过实验验证了我们关于表现力的理论发现。此外，我们还证明了DropGNN在已建立的GNN基准上具有竞争力。 摘要：This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs of a GNN on the input graph, with some of the nodes randomly and independently dropped in each of these runs. Then, we combine the results of these runs to obtain the final result. We prove that DropGNNs can distinguish various graph neighborhoods that cannot be separated by message passing GNNs. We derive theoretical bounds for the number of runs required to ensure a reliable distribution of dropouts, and we prove several properties regarding the expressive capabilities and limits of DropGNNs. We experimentally validate our theoretical findings on expressiveness. Furthermore, we show that DropGNNs perform competitively on established GNN benchmarks.

【4】 Generalizable Cross-Graph Embedding for GNN-based Congestion Prediction 标题：基于GNN的拥塞预测的广义交图嵌入 链接：https://arxiv.org/abs/2111.05941

作者：Amur Ghose,Vincent Zhang,Yingxue Zhang,Dong Li,Wulong Liu,Mark Coates 机构： Huawei ‡ McGill University 备注：Accepted and presented at ICCAD 2021 摘要：目前，随着技术节点的扩展，早期设计阶段的准确预测模型可以显著缩短设计周期。特别是在逻辑综合过程中，预测由于逻辑组合不当而导致的单元拥塞可以减少后续物理实现的负担。在逻辑综合阶段，有人尝试使用图形神经网络（GNN）技术处理拥塞预测问题。然而，由于GNNs的核心思想是建立在消息传递框架上的，这在早期逻辑综合阶段是不切实际的，因此它们需要信息单元特性来实现合理的性能。为了解决这个限制，我们提出了一个框架，可以直接学习给定网络列表的嵌入，以提高节点特性的质量。流行的基于随机游走的嵌入方法，如Node2vec、LINE和DeepWalk，都存在交叉图对齐问题和对看不见的网表图的泛化能力差的问题，导致性能低下，并耗费大量运行时间。在我们的框架中，我们引入了一种更好的方法来获得节点嵌入，它可以使用矩阵分解方法在网络列表图中进行推广。提出了一种有效的子图级小批量训练方法，该方法既能保证并行训练，又能满足大规模网表的内存限制。我们利用开源EDA工具（如DREAMPLACE和OPENROAD框架）在各种公开可用的电路上展示结果。通过将学习到的嵌入在网络列表顶部与GNN相结合，我们的方法提高了预测性能，推广到新的电路线路，并且训练效率高，潜在地节省了90%以上的运行时间。 摘要：Presently with technology node scaling, an accurate prediction model at early design stages can significantly reduce the design cycle. Especially during logic synthesis, predicting cell congestion due to improper logic combination can reduce the burden of subsequent physical implementations. There have been attempts using Graph Neural Network (GNN) techniques to tackle congestion prediction during the logic synthesis stage. However, they require informative cell features to achieve reasonable performance since the core idea of GNNs is built on the message passing framework, which would be impractical at the early logic synthesis stage. To address this limitation, we propose a framework that can directly learn embeddings for the given netlist to enhance the quality of our node features. Popular random-walk based embedding methods such as Node2vec, LINE, and DeepWalk suffer from the issue of cross-graph alignment and poor generalization to unseen netlist graphs, yielding inferior performance and costing significant runtime. In our framework, we introduce a superior alternative to obtain node embeddings that can generalize across netlist graphs using matrix factorization methods. We propose an efficient mini-batch training method at the sub-graph level that can guarantee parallel training and satisfy the memory restriction for large-scale netlists. We present results utilizing open-source EDA tools such as DREAMPLACE and OPENROAD frameworks on a variety of openly available circuits. By combining the learned embedding on top of the netlist with the GNNs, our method improves prediction performance, generalizes to new circuit lines, and is efficient in training, potentially saving over $90 \%$ of runtime.

【5】 SPA-GCN: Efficient and Flexible GCN Accelerator with an Application for Graph Similarity Computation 标题：SPA-GCN：高效灵活的GCN加速器及其在图相似度计算中的应用 链接：https://arxiv.org/abs/2111.05936

作者：Atefeh Sohrabizadeh,Yuze Chi,Jason Cong 机构：Computer Science Department, University of California, Los Angeles, USA 备注：12 pages 摘要：虽然已经有许多关于图像深度学习硬件加速的研究，但对于加速涉及图形的深度学习应用程序的研究却相当有限。图形的独特特性，如不规则的内存访问和动态并行性，在将算法映射到CPU或GPU时带来了一些挑战。为了在利用所有可用稀疏性的同时解决这些挑战，我们提出了一种称为SPA-GCN的灵活体系结构，用于加速图卷积网络（GCN），这是图上深度学习算法的核心计算单元。该体系结构专门用于处理许多小图，因为图的大小对设计考虑有重大影响。在此背景下，我们使用基于神经网络的图匹配算法SimGNN作为案例研究，以证明我们的体系结构的有效性。实验结果表明，与多核CPU实现和GPU实现相比，SPA-GCN具有较高的加速比，表明了我们设计的有效性。 摘要：While there have been many studies on hardware acceleration for deep learning on images, there has been a rather limited focus on accelerating deep learning applications involving graphs. The unique characteristics of graphs, such as the irregular memory access and dynamic parallelism, impose several challenges when the algorithm is mapped to a CPU or GPU. To address these challenges while exploiting all the available sparsity, we propose a flexible architecture called SPA-GCN for accelerating Graph Convolutional Networks (GCN), the core computation unit in deep learning algorithms on graphs. The architecture is specialized for dealing with many small graphs since the graph size has a significant impact on design considerations. In this context, we use SimGNN, a neural-network-based graph matching algorithm, as a case study to demonstrate the effectiveness of our architecture. The experimental results demonstrate that SPA-GCN can deliver a high speedup compared to a multi-core CPU implementation and a GPU implementation, showing the efficiency of our design.

【6】 Graph Neural Network Training with Data Tiering 标题：基于数据分层的图神经网络训练 链接：https://arxiv.org/abs/2111.05894

作者：Seung Won Min,Kun Wu,Mert Hidayetoğlu,Jinjun Xiong,Xiang Song,Wen-mei Hwu 机构： 20 19)and the graphs with such scales make the ordinary na¨ıve 1University of Illinois at Urbana-Champaign 2University ofBuffalo 3AWS Shanghai AI Lab 4NVIDIA 摘要：图神经网络（GNNs）在从图结构数据学习方面取得了成功，并应用于欺诈检测、推荐和知识图推理。然而，有效地训练GNN是一项挑战，因为：1）GPU内存容量有限，无法满足大型数据集的需要；2）基于图形的数据结构导致不规则的数据访问模式。在这项工作中，我们提供了一种在GNN训练之前统计分析和识别更频繁访问的数据的方法。我们的数据分层方法不仅利用了输入图的结构，还利用了从实际GNN训练过程中获得的洞察力，以获得更高的预测结果。通过我们的数据分层方法，我们还提供了一种新的数据放置和访问策略，以进一步最小化CPU-GPU通信开销。我们还考虑了多GPU GNN训练，并在多GPU系统中演示了我们的策略的有效性。评估结果表明，我们的工作减少了87-95%的CPU-GPU通信量，在具有数亿个节点和数十亿条边的图形上，GNN的训练速度比现有解决方案提高了1.6-2.1x。 摘要：Graph Neural Networks (GNNs) have shown success in learning from graph-structured data, with applications to fraud detection, recommendation, and knowledge graph reasoning. However, training GNN efficiently is challenging because: 1) GPU memory capacity is limited and can be insufficient for large datasets, and 2) the graph-based data structure causes irregular data access patterns. In this work, we provide a method to statistical analyze and identify more frequently accessed data ahead of GNN training. Our data tiering method not only utilizes the structure of input graph, but also an insight gained from actual GNN training process to achieve a higher prediction result. With our data tiering method, we additionally provide a new data placement and access strategy to further minimize the CPU-GPU communication overhead. We also take into account of multi-GPU GNN training as well and we demonstrate the effectiveness of our strategy in a multi-GPU system. The evaluation results show that our work reduces CPU-GPU traffic by 87-95% and improves the training speed of GNN over the existing solutions by 1.6-2.1x on graphs with hundreds of millions of nodes and billions of edges.

【7】 Predicting Lattice Phonon Vibrational Frequencies Using Deep Graph Neural Networks 标题：用深度图神经网络预测晶格声子振动频率 链接：https://arxiv.org/abs/2111.05885

作者：Nghia Nguyen,Steph-Yves Louis,Lai Wei,Kamal Choudhary,Ming Hu,Jianjun Hu 机构：Department of Computer Science and Engineering, University of South Carolina, Columbia, SC , Materials Science and Engineering Division, National Institute of Standards and Technology, Gaithersburg, MD, Theiss Research, La Jolla, CA 备注：9 pages 摘要：晶格振动频率与许多重要的材料性质有关，如热导率、电导率以及超导电性。然而，在材料筛选中，使用密度泛函理论（DFT）方法计算振动频率对大量样本的计算要求太高。在这里，我们提出了一种基于深度图神经网络的算法，用于从晶体结构中高精度预测晶体振动频率。我们的算法使用零填充方案解决振动频谱的可变维问题。对15000和35552个样本的两个数据集的基准研究表明，预测的合计$R^2$分数分别达到0.554和0.724。我们的工作证明了深图神经网络能够学习预测晶体结构的声子谱特性，以及输出维数恒定的声子态密度（DOS）和电子DOS。 摘要：Lattice vibration frequencies are related to many important materials properties such as thermal and electrical conductivity as well as superconductivity. However, computational calculation of vibration frequencies using density functional theory (DFT) methods is too computationally demanding for a large number of samples in materials screening. Here we propose a deep graph neural network-based algorithm for predicting crystal vibration frequencies from crystal structures with high accuracy. Our algorithm addresses the variable dimension of vibration frequency spectrum using the zero padding scheme. Benchmark studies on two data sets with 15,000 and 35,552 samples show that the aggregated $R^2$ scores of the prediction reaches 0.554 and 0.724 respectively. Our work demonstrates the capability of deep graph neural networks to learn to predict phonon spectrum properties of crystal structures in addition to phonon density of states (DOS) and electronic DOS in which the output dimension is constant.

Transformer(2篇)

【1】 CubeTR: Learning to Solve The Rubiks Cube Using Transformers 标题：CubeTR：学习使用Transformer求解魔方 链接：https://arxiv.org/abs/2111.06036

作者：Mustafa Ebrahim Chasmai 机构： ChasmaiDepartment of Computer Science and EngineeringIndian Institute of Technology DelhiHauz Khas 摘要：自第一次出现以来，Transformer已经成功地应用于从计算机视觉到自然语言处理的广泛领域。Transformer在强化学习中的应用是最近才提出的，它是通过将其重新表述为序列建模问题来实现的。与其他常见的强化学习问题相比，Rubiks立方体提出了一系列独特的挑战。Rubiks立方体有一个五分之一可能配置的单一求解状态，这会导致非常稀疏的奖励。提出的CubeTR模型关注较长的动作序列，并解决了稀疏奖励问题。CubeTR学习如何在没有任何人类先验知识的情况下从任意起始状态求解Rubiks立方体，并且在移动正则化之后，由其生成的解的长度预计将非常接近由专家人类解算器使用的算法给出的解的长度。CubeTR提供了学习算法对高维立方体的通用性以及Transformer在其他相关稀疏奖励场景中的适用性的见解。 摘要：Since its first appearance, transformers have been successfully used in wide ranging domains from computer vision to natural language processing. Application of transformers in Reinforcement Learning by reformulating it as a sequence modelling problem was proposed only recently. Compared to other commonly explored reinforcement learning problems, the Rubiks cube poses a unique set of challenges. The Rubiks cube has a single solved state for quintillions of possible configurations which leads to extremely sparse rewards. The proposed model CubeTR attends to longer sequences of actions and addresses the problem of sparse rewards. CubeTR learns how to solve the Rubiks cube from arbitrary starting states without any human prior, and after move regularisation, the lengths of solutions generated by it are expected to be very close to those given by algorithms used by expert human solvers. CubeTR provides insights to the generalisability of learning algorithms to higher dimensional cubes and the applicability of transformers in other relevant sparse reward scenarios.

【2】 Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word 标题：软测量Transformer：数百个传感器值一句话 链接：https://arxiv.org/abs/2111.05973

作者：Chao Zhang,Jaswanth Yella,Yu Huang,Xiaoye Qian,Sergei Petrov,Andrey Rzhetsky,Sthitie Bom 机构：Seagate Technology, MN, US, University of Chicago, IL, US, University of Cincinnati, OH, US, Florida Atlantic University, FL, US, Case Western Reserve University, OH, US, Stanford University, CA, US 摘要：近年来，随着人工智能技术的飞速发展，在软测量领域已经有很多关于深度学习模型的研究。然而，模型变得更加复杂，但数据集仍然有限：研究人员正在用数百个数据样本拟合百万参数模型，这不足以证明其模型的有效性，因此在工业应用中实施时往往无法执行。为了解决这个长期存在的问题，我们向公众提供希捷科技的大规模、高维时间序列制造传感器数据。我们展示了在这些数据集上通过软测量Transformer模型对工业大数据建模的挑战和有效性。之所以使用Transformer，是因为它在自然语言处理方面的表现优于最先进的技术，并且从那时起，它在直接应用于计算机视觉方面也表现良好，而不引入图像特定的电感偏置。我们观察句子结构与传感器读数的相似性，并以自然语言中类似的句子方式处理时间序列中的多变量传感器读数。高维时间序列数据被格式化成相同形状的嵌入句子，并输入到转换器模型中。结果表明，Transformer模型在基于自动编码器和长短时记忆（LSTM）模型的软测量领域优于基准模型。据我们所知，我们是学术界或工业界第一个利用大规模数值软测量数据对原始Transformer模型的性能进行基准测试的团队。 摘要：With the rapid development of AI technology in recent years, there have been many studies with deep learning models in soft sensing area. However, the models have become more complex, yet, the data sets remain limited: researchers are fitting million-parameter models with hundreds of data samples, which is insufficient to exercise the effectiveness of their models and thus often fail to perform when implemented in industrial applications. To solve this long-lasting problem, we are providing large scale, high dimensional time series manufacturing sensor data from Seagate Technology to the public. We demonstrate the challenges and effectiveness of modeling industrial big data by a Soft Sensing Transformer model on these data sets. Transformer is used because, it has outperformed state-of-the-art techniques in Natural Language Processing, and since then has also performed well in the direct application to computer vision without introduction of image-specific inductive biases. We observe the similarity of a sentence structure to the sensor readings and process the multi-variable sensor readings in a time series in a similar manner of sentences in natural language. The high-dimensional time-series data is formatted into the same shape of embedded sentences and fed into the transformer model. The results show that transformer model outperforms the benchmark models in soft sensing field based on auto-encoder and long short-term memory (LSTM) models. To the best of our knowledge, we are the first team in academia or industry to benchmark the performance of original transformer model with large-scale numerical soft sensing data.

GAN|对抗|攻击|生成相关(3篇)

【1】 Feature Generation for Long-tail Classification 标题：面向长尾分类的特征生成 链接：https://arxiv.org/abs/2111.05956

作者：Rahul Vigneswaran,Marc T. Law,Vineeth N. Balasubramanian,Makarand Tapaswi 机构：Indian Institute of Technology, Hyderabad, NVIDIA, IIIT Hyderabad, India 备注：Accepted at ICVGIP'21. Code available at this https URL 摘要：视觉世界自然会表现出对象或场景实例数量的不平衡，从而导致长尾分布。这种不平衡对基于深度学习的分类模型提出了重大挑战。tail类的过采样实例试图解决这种不平衡。然而，有限的视觉多样性导致网络表现能力差。一个简单的解决方法是解耦表示和分类器网络，并仅使用过采样来训练分类器。在本文中，我们探索了一个方向，即通过估计尾部类别的分布来尝试生成有意义的特征，而不是重复地对同一图像（以及因此产生的特征）进行重新采样。受最近关于Few-Shot学习的工作的启发，我们创建了校准分布，以对随后用于训练分类器的附加特征进行采样。通过在具有不同不平衡因子的CIFAR-100-LT（长尾）数据集和mini-ImageNet LT（长尾）数据集上的若干实验，我们展示了我们的方法的有效性，并建立了一个新的最新技术。我们还使用t-SNE可视化对生成的特征进行定性分析，并分析用于校准尾类分布的最近邻。我们的代码可在https://github.com/rahulvigneswaran/TailCalibX. 摘要：The visual world naturally exhibits an imbalance in the number of object or scene instances resulting in a \emph{long-tailed distribution}. This imbalance poses significant challenges for classification models based on deep learning. Oversampling instances of the tail classes attempts to solve this imbalance. However, the limited visual diversity results in a network with poor representation ability. A simple counter to this is decoupling the representation and classifier networks and using oversampling only to train the classifier. In this paper, instead of repeatedly re-sampling the same image (and thereby features), we explore a direction that attempts to generate meaningful features by estimating the tail category's distribution. Inspired by ideas from recent work on few-shot learning, we create calibrated distributions to sample additional features that are subsequently used to train the classifier. Through several experiments on the CIFAR-100-LT (long-tail) dataset with varying imbalance factors and on mini-ImageNet-LT (long-tail), we show the efficacy of our approach and establish a new state-of-the-art. We also present a qualitative analysis of generated features using t-SNE visualizations and analyze the nearest neighbors used to calibrate the tail class distributions. Our code is available at https://github.com/rahulvigneswaran/TailCalibX.

【2】 Kalman Filtering with Adversarial Corruptions 标题：对抗性腐蚀下的卡尔曼滤波 链接：https://arxiv.org/abs/2111.06395

作者：Sitan Chen,Frederic Koehler,Ankur Moitra,Morris Yau 机构：UC Berkeley, MIT 备注：57 pages, comments welcome 摘要：在这里，我们回顾了线性二次估计的经典问题，即从噪声测量估计线性动力系统的轨迹。当测量噪声为高斯噪声时，著名的卡尔曼滤波器给出了最佳估计量，但众所周知，当偏离此假设时（例如，当噪声为重尾噪声时），卡尔曼滤波器会出现故障。许多特别的启发式方法在实践中被用于处理异常值。在一项开创性的工作中，Schick和Mitter给出了当测量噪声是高斯函数的已知无穷小扰动时的可证明保证，并提出了一个重要问题，即对于大扰动和未知扰动，是否可以获得类似的保证。在这项工作中，我们给出了一个真正鲁棒的滤波器：我们给出了线性二次估计的第一个强可证明的保证，即使是一个常数部分的测量已经被不利地破坏。该框架可以模拟重尾甚至非平稳噪声过程。我们的算法证明了卡尔曼滤波器的鲁棒性，因为它与知道腐蚀位置的最优算法相竞争。我们的工作是在一个具有挑战性的贝叶斯环境中进行的，在这个环境中，测量的数量随着我们需要估计的复杂性而变化。此外，在线性动力系统中，过去的信息会随着时间而衰减。我们开发了一套新技术，能够在不同的时间步长和不同的时间尺度上稳健地提取信息。 摘要：Here we revisit the classic problem of linear quadratic estimation, i.e. estimating the trajectory of a linear dynamical system from noisy measurements. The celebrated Kalman filter gives an optimal estimator when the measurement noise is Gaussian, but is widely known to break down when one deviates from this assumption, e.g. when the noise is heavy-tailed. Many ad hoc heuristics have been employed in practice for dealing with outliers. In a pioneering work, Schick and Mitter gave provable guarantees when the measurement noise is a known infinitesimal perturbation of a Gaussian and raised the important question of whether one can get similar guarantees for large and unknown perturbations. In this work we give a truly robust filter: we give the first strong provable guarantees for linear quadratic estimation when even a constant fraction of measurements have been adversarially corrupted. This framework can model heavy-tailed and even non-stationary noise processes. Our algorithm robustifies the Kalman filter in the sense that it competes with the optimal algorithm that knows the locations of the corruptions. Our work is in a challenging Bayesian setting where the number of measurements scales with the complexity of what we need to estimate. Moreover, in linear dynamical systems past information decays over time. We develop a suite of new techniques to robustly extract information across different time steps and over varying time scales.

【3】 Adversarial sampling of unknown and high-dimensional conditional distributions 标题：未知和高维条件分布的对抗性抽样 链接：https://arxiv.org/abs/2111.05962

作者：Malik Hassanaly,Andrew Glaws,Karen Stengel,Ryan N. King 备注：26 pages, 12 figures, 4 tables 摘要：许多工程问题需要预测实现到实现的可变性或对建模数量的精确描述。在这种情况下，有必要从可能具有数百万自由度的未知高维空间中采样元素。虽然存在能够从已知形状的概率密度函数（PDF）中采样元素的方法，但当分布未知时，需要进行几种近似。在本文中，采样方法以及对基础分布的推断都使用了一种称为生成对抗网络（GAN）的数据驱动方法进行处理，该方法训练两个相互竞争的神经网络，以生成一个网络，该网络可以有效地从训练集分布生成样本。在实践中，经常需要从条件分布中抽取样本。当条件变量连续时，可能只有一个（如果有）数据点对应于条件变量的特定值，这不足以估计条件分布。这项工作处理这个问题，使用先验估计的条件矩的PDF。比较了随机估计和外部神经网络两种计算这些矩的方法；但是，可以使用任何首选方法。该算法以过滤后的湍流流场的反褶积为例进行了验证。结果表明，与现有方法相比，该算法的所有版本都能有效地对目标条件分布进行采样，且对样本质量的影响最小。此外，该程序还可用作由具有连续变量的条件GAN（cGAN）生成的样本多样性的度量。 摘要：Many engineering problems require the prediction of realization-to-realization variability or a refined description of modeled quantities. In that case, it is necessary to sample elements from unknown high-dimensional spaces with possibly millions of degrees of freedom. While there exist methods able to sample elements from probability density functions (PDF) with known shapes, several approximations need to be made when the distribution is unknown. In this paper the sampling method, as well as the inference of the underlying distribution, are both handled with a data-driven method known as generative adversarial networks (GAN), which trains two competing neural networks to produce a network that can effectively generate samples from the training set distribution. In practice, it is often necessary to draw samples from conditional distributions. When the conditional variables are continuous, only one (if any) data point corresponding to a particular value of a conditioning variable may be available, which is not sufficient to estimate the conditional distribution. This work handles this problem using an a priori estimation of the conditional moments of a PDF. Two approaches, stochastic estimation, and an external neural network are compared here for computing these moments; however, any preferred method can be used. The algorithm is demonstrated in the case of the deconvolution of a filtered turbulent flow field. It is shown that all the versions of the proposed algorithm effectively sample the target conditional distribution with minimal impact on the quality of the samples compared to state-of-the-art methods. Additionally, the procedure can be used as a metric for the diversity of samples generated by a conditional GAN (cGAN) conditioned with continuous variables.

半/弱/无/有监督|不确定性|主动学习(5篇)

【1】 Unsupervised Part Discovery from Contrastive Reconstruction 标题：基于对比重建的无监督部分发现 链接：https://arxiv.org/abs/2111.06349

作者：Subhabrata Choudhury,Iro Laina,Christian Rupprecht,Andrea Vedaldi 机构：Visual Geometry Group, University of Oxford, Oxford, UK 备注：To appear in NeurIPS 2021. Project page: this https URL 摘要：自监督视觉表征学习的目标是学习强的、可转移的图像表征，大多数研究集中在对象或场景层面。另一方面，部分水平的表征学习受到的关注明显较少。在本文中，我们提出了一种无监督的对象部分发现和分割方法，并做出了三点贡献。首先，我们通过一组目标构造一个代理任务，这些目标鼓励模型学习将图像有意义地分解为各个部分。其次，先前的工作主张重建或聚类预先计算的特征作为零件的代理；我们的经验表明，仅此一点不太可能找到有意义的部分；这主要是因为它们的低分辨率和分类网络在空间上抹去信息的趋势。我们认为，在像素级的图像重建可以缓解这个问题，作为一个补充线索。最后，我们证明了基于关键点回归的标准评估与分割质量没有很好的相关性，因此引入了不同的度量，NMI和ARI，可以更好地描述对象分解为多个部分。我们的方法产生的语义部分在细粒度但视觉上不同的类别中是一致的，在三个基准数据集上优于最新水平。代码位于项目页面：https://www.robots.ox.ac.uk/~vgg/研究/不明嫌犯零件/。 摘要：The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has received significantly less attention. In this paper, we propose an unsupervised approach to object part discovery and segmentation and make three contributions. First, we construct a proxy task through a set of objectives that encourages the model to learn a meaningful decomposition of the image into its parts. Secondly, prior work argues for reconstructing or clustering pre-computed features as a proxy to parts; we show empirically that this alone is unlikely to find meaningful parts; mainly because of their low resolution and the tendency of classification networks to spatially smear out information. We suggest that image reconstruction at the level of pixels can alleviate this problem, acting as a complementary cue. Lastly, we show that the standard evaluation based on keypoint regression does not correlate well with segmentation quality and thus introduce different metrics, NMI and ARI, that better characterize the decomposition of objects into parts. Our method yields semantic parts which are consistent across fine-grained but visually distinct categories, outperforming the state of the art on three benchmark datasets. Code is available at the project page: https://www.robots.ox.ac.uk/~vgg/research/unsup-parts/.

【2】 Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport 标题：基于鉴别器约束最优传输的无监督噪声自适应语音增强 链接：https://arxiv.org/abs/2111.06316

作者：Hsin-Yi Lin,Huan-Hsin Tseng,Xugang Lu,Yu Tsao 机构：The Cooperative Institute for Research in Environmental Sciences (CIRES), University of Colorado, Boulder, CO, USA, NOAA Physical Sciences Laboratory, Boulder, CO, USA, Research Center for Information Technology Innovation, Academia Sinica, Taiwan 备注：Accepted at NeurIPS 2021 摘要：本文提出了一种新的鉴别器约束最优传输网络（DOTN），该网络对语音增强（SE）进行无监督域自适应，这是语音处理中的一项基本回归任务。DOTN旨在利用源域的可用知识，估计目标域中噪声语音的干净参考。据报道，训练和测试数据之间的领域转移是学习不同领域问题的障碍。尽管存在大量关于无监督领域自适应分类的文献，但所提出的方法，特别是在回归中，仍然很少，并且通常依赖于有关输入数据的附加信息。提出的DOTN方法策略性地将数学分析中的最优传输（OT）理论与生成性对抗框架相融合，以帮助评估目标域中的连续标签。在两个SE任务上的实验结果表明，通过扩展经典的OT公式，我们提出的DOTN在纯无监督的方式下优于以前的对抗性领域适应框架。 摘要：This paper presents a novel discriminator-constrained optimal transport network (DOTN) that performs unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing. The DOTN aims to estimate clean references of noisy speech in a target domain, by exploiting the knowledge available from the source domain. The domain shift between training and testing data has been reported to be an obstacle to learning problems in diverse fields. Although rich literature exists on unsupervised domain adaptation for classification, the methods proposed, especially in regressions, remain scarce and often depend on additional information regarding the input data. The proposed DOTN approach tactically fuses the optimal transport (OT) theory from mathematical analysis with generative adversarial frameworks, to help evaluate continuous labels in the target domain. The experimental results on two SE tasks demonstrate that by extending the classical OT formulation, our proposed DOTN outperforms previous adversarial domain adaptation frameworks in a purely unsupervised manner.

【3】 Dense Unsupervised Learning for Video Segmentation 标题：密集无监督学习在视频分割中的应用 链接：https://arxiv.org/abs/2111.06265

作者：Nikita Araslanov,Simone Schaub-Meyer,Stefan Roth 机构：Department of Computer Science, TU Darmstadt, hessian.AI 备注：To appear at NeurIPS*2021. Code: this https URL 摘要：提出了一种新的无监督学习视频对象分割方法。与以前的工作不同，我们的公式允许在完全卷积区域中直接学习密集特征表示。我们依靠均匀网格采样来提取一组锚，并训练我们的模型在视频间和视频内消除它们之间的歧义。然而，训练这样一个模型的简单方案会导致退化解。我们建议通过一个简单的正则化方案来防止这种情况，该方案将分割任务的等变特性与相似性变换相适应。我们的训练目标允许高效实施，并显示出快速的训练融合。在已建立的VOS基准上，尽管使用的训练数据和计算能力显著减少，但我们的方法超过了以前工作的分割精度。 摘要：We present a novel approach to unsupervised learning for video object segmentation (VOS). Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. We rely on uniform grid sampling to extract a set of anchors and train our model to disambiguate between them on both inter- and intra-video levels. However, a naive scheme to train such a model results in a degenerate solution. We propose to prevent this with a simple regularisation scheme, accommodating the equivariance property of the segmentation task to similarity transformations. Our training objective admits efficient implementation and exhibits fast training convergence. On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.

【4】 Uncertainty quantification of a 3D In-Stent Restenosis model with surrogate modelling 标题：用代理建模法量化三维支架内再狭窄模型的不确定性 链接：https://arxiv.org/abs/2111.06173

作者：Dongwei Ye,Pavel Zun,Valeria Krzhizhanovskaya,Alfons G. Hoekstra 机构：Computational Science Lab, Institute for Informatics, University of Amsterdam, The Netherlands, National Center for Cognitive Research, ITMO University, Saint Petersburg, Russia 摘要：支架内再狭窄是由于球囊扩张和支架置入引起的血管损伤导致冠状动脉狭窄的复发。它可能导致心绞痛症状的复发或急性冠状动脉综合征。提出了一种支架内再狭窄模型的不确定性量化方法，该模型具有四个不确定参数（内皮细胞再生时间、平滑肌细胞键断裂的阈值应变、血流速度和内部弹性层中的开窗百分比）。研究了两个感兴趣的量，即容器中的平均横截面积和最大相对面积损失。由于模型的计算强度和不确定性量化所需的评估数量，开发了基于高斯过程回归和适当正交分解的替代模型，该模型随后取代了不确定性量化中的原始支架内再狭窄模型。详细分析了不确定性传播和灵敏度分析。平均横截面积和最大相对面积损失的不确定性分别约为11%和16%，不确定性估计表明，较高的开窗率主要决定了过程初始阶段新生内膜生长的不确定性。另一方面，血流速度和内皮细胞再生时间的不确定性主要决定了再狭窄过程后期临床相关阶段的相关数量的不确定性。与其他不确定参数相比，阈值应变的不确定性相对较小。 摘要：In-Stent Restenosis is a recurrence of coronary artery narrowing due to vascular injury caused by balloon dilation and stent placement. It may lead to the relapse of angina symptoms or to an acute coronary syndrome. An uncertainty quantification of a model for In-Stent Restenosis with four uncertain parameters (endothelium regeneration time, the threshold strain for smooth muscle cells bond breaking, blood flow velocity and the percentage of fenestration in the internal elastic lamina) is presented. Two quantities of interest were studied, namely the average cross-sectional area and the maximum relative area loss in a vessel. Due to the computational intensity of the model and the number of evaluations required in the uncertainty quantification, a surrogate model, based on Gaussian process regression with proper orthogonal decomposition, was developed which subsequently replaced the original In-Stent Restenosis model in the uncertainty quantification. A detailed analysis of the uncertainty propagation and sensitivity analysis is presented. Around 11% and 16% of uncertainty are observed on the average cross-sectional area and maximum relative area loss respectively, and the uncertainty estimates show that a higher fenestration mainly determines uncertainty in the neointimal growth at the initial stage of the process. On the other hand, the uncertainty in blood flow velocity and endothelium regeneration time mainly determine the uncertainty in the quantities of interest at the later, clinically relevant stages of the restenosis process. The uncertainty in the threshold strain is relatively small compared to the other uncertain parameters.

【5】 Trustworthy Medical Segmentation with Uncertainty Estimation 标题：基于不确定性估计的可信医学分割 链接：https://arxiv.org/abs/2111.05978

作者：Giuseppina Carannante,Dimah Dera,Nidhal C. Bouaynaya,Rasool Ghulam,Hassan M. Fathallah-Shaykh 机构： University of Texas Rio Grande Valley 摘要：深度学习（DL）由于其精确性、效率和客观性，在重塑医疗系统方面具有巨大的前景。然而，DL模型对噪声和分布外输入的脆弱性阻碍了其在临床上的应用。大多数系统在没有关于模型不确定性或置信度的进一步信息的情况下产生点估计。本文介绍了一种新的用于分段神经网络不确定性量化的贝叶斯深度学习框架，特别是编码器-解码器结构。该框架使用一阶泰勒级数近似，通过最大化证据下界来传播和学习给定训练数据的模型参数分布的前两个矩（均值和协方差）。输出包括两个映射：分割图像和分割的不确定性映射。分割决策中的不确定性由预测分布的协方差矩阵捕获。我们评估了基于磁共振成像和计算机断层扫描的医学图像分割数据的框架。我们在多个基准数据集上的实验表明，与最先进的分割模型相比，该框架对噪声和对抗性攻击更具鲁棒性。此外，所提出框架的不确定性映射将低置信度（或相当高的不确定性）与测试输入图像中被噪声、伪影或敌对攻击破坏的补丁相关联。因此，当模型做出错误预测或遗漏部分分割结构（例如肿瘤）时，通过在不确定性图中呈现更高的值，模型可以自我评估其分割决策。 摘要：Deep Learning (DL) holds great promise in reshaping the healthcare systems given its precision, efficiency, and objectivity. However, the brittleness of DL models to noisy and out-of-distribution inputs is ailing their deployment in the clinic. Most systems produce point estimates without further information about model uncertainty or confidence. This paper introduces a new Bayesian deep learning framework for uncertainty quantification in segmentation neural networks, specifically encoder-decoder architectures. The proposed framework uses the first-order Taylor series approximation to propagate and learn the first two moments (mean and covariance) of the distribution of the model parameters given the training data by maximizing the evidence lower bound. The output consists of two maps: the segmented image and the uncertainty map of the segmentation. The uncertainty in the segmentation decisions is captured by the covariance matrix of the predictive distribution. We evaluate the proposed framework on medical image segmentation data from Magnetic Resonances Imaging and Computed Tomography scans. Our experiments on multiple benchmark datasets demonstrate that the proposed framework is more robust to noise and adversarial attacks as compared to state-of-the-art segmentation models. Moreover, the uncertainty map of the proposed framework associates low confidence (or equivalently high uncertainty) to patches in the test input images that are corrupted with noise, artifacts or adversarial attacks. Thus, the model can self-assess its segmentation decisions when it makes an erroneous prediction or misses part of the segmentation structures, e.g., tumor, by presenting higher values in the uncertainty map.

迁移|Zero/Few/One-Shot|自适应(2篇)

【1】 The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos 标题：客观性的出现：从视频中学习Zero-Shot分割 链接：https://arxiv.org/abs/2111.06394

作者：Runtao Liu,Zhirong Wu,Stella X. Yu,Stephen Lin 机构：Microsoft Research Asia, John Hopkins University, UC Berkeley ICSI 备注：This paper has been accepted to NeurIPS 2021 摘要：人类可以很容易地分割移动的物体，而不知道它们是什么。连续的视觉观察可能产生的对象性促使我们同时从未标记的视频中建模分组和运动。我们的前提是，一个视频在同一场景中有不同的视图，这些视图由移动组件关联，正确的区域分割和区域流将允许相互视图合成，而无需任何外部监督即可从数据本身进行检查。我们的模型从两个独立的路径开始：一个外观路径为单个图像输出基于特征的区域分割，另一个运动路径为一对图像输出运动特征。然后，它将它们绑定到称为“分段流”的联合表示中，该表示汇集每个区域上的流偏移，并为整个场景提供移动区域的总体特征。通过训练模型以最小化基于片段流的视图合成误差，我们的外观和运动路径自动学习区域分割和流估计，而无需分别从低级边缘或光流建立它们。我们的模型展示了外观路径中令人惊讶的对象性的出现，超过了以前在图像Zero-Shot对象分割、无监督测试时间自适应视频运动对象分割和监督微调语义图像分割方面的工作。我们的工作是第一个真正的端到端Zero-Shot视频对象分割。它不仅为分割和跟踪提供了通用的对象性，而且在没有增强工程的情况下，它的性能也优于目前流行的基于图像的对比学习方法。 摘要：Humans can easily segment moving objects without knowing what they are. That objectness could emerge from continuous visual observations motivates us to model grouping and movement concurrently from unlabeled videos. Our premise is that a video has different views of the same scene related by moving components, and the right region segmentation and region flow would allow mutual view synthesis which can be checked from the data itself without any external supervision. Our model starts with two separate pathways: an appearance pathway that outputs feature-based region segmentation for a single image, and a motion pathway that outputs motion features for a pair of images. It then binds them in a conjoint representation called segment flow that pools flow offsets over each region and provides a gross characterization of moving regions for the entire scene. By training the model to minimize view synthesis errors based on segment flow, our appearance and motion pathways learn region segmentation and flow estimation automatically without building them up from low-level edges or optical flows respectively. Our model demonstrates the surprising emergence of objectness in the appearance pathway, surpassing prior works on zero-shot object segmentation from an image, moving object segmentation from a video with unsupervised test-time adaptation, and semantic image segmentation by supervised fine-tuning. Our work is the first truly end-to-end zero-shot object segmentation from videos. It not only develops generic objectness for segmentation and tracking, but also outperforms prevalent image-based contrastive learning methods without augmentation engineering.

【2】 A Meta-Method for Portfolio Management Using Machine Learning for Adaptive Strategy Selection 标题：一种基于机器学习自适应策略选择的投资组合管理元方法 链接：https://arxiv.org/abs/2111.05935

作者：Damian Kisiel,Denise Gorse 机构：University College London, Department of Computer Science, London, United Kingdom 备注：5 pages 摘要：这项工作提出了一种新的投资组合管理技术，元投资组合方法（MPM），其灵感来源于生物信息学和其他领域中元方法的成功。MPM使用XGBoost学习如何在两种基于风险的投资组合分配策略（层次风险平价（HRP）和更经典的自然风险平价（NRP）之间切换。实践证明，MPM能够成功利用每种策略的最佳特征（NRP在市场上升趋势期间快速增长，HRP在市场动荡期间防止提款）。因此，MPM被证明具有极好的样本外风险回报曲线（通过夏普比率衡量），此外还提供了其资产配置决策的高度可解释性。 摘要：This work proposes a novel portfolio management technique, the Meta Portfolio Method (MPM), inspired by the successes of meta approaches in the field of bioinformatics and elsewhere. The MPM uses XGBoost to learn how to switch between two risk-based portfolio allocation strategies, the Hierarchical Risk Parity (HRP) and more classical Na\"ive Risk Parity (NRP). It is demonstrated that the MPM is able to successfully take advantage of the best characteristics of each strategy (the NRP's fast growth during market uptrends, and the HRP's protection against drawdowns during market turmoil). As a result, the MPM is shown to possess an excellent out-of-sample risk-reward profile, as measured by the Sharpe ratio, and in addition offers a high degree of interpretability of its asset allocation decisions.

强化学习(5篇)

【1】 Multi-agent Reinforcement Learning for Cooperative Lane Changing of Connected and Autonomous Vehicles in Mixed Traffic 标题：混合交通中连通自主车辆协同变道的多智能体强化学习 链接：https://arxiv.org/abs/2111.06318

作者：Wei Zhou,Dong Chen,Jun Yan,Zhaojian Li,Huilin Yin,Wanchen Ge 机构：School of Electronic and Information Engineering, Tongji, University, Caoangong Street, Shanghai, China., Mechanical Engineering, Michigan State University, Lansing, USA., †These authors contributed equally to this work. 摘要：在过去的二十年中，自动驾驶吸引了大量的研究兴趣，因为它提供了许多潜在的好处，包括使驾驶员免于疲劳驾驶和缓解交通拥堵等。尽管取得了可喜的进展，车道变换仍然是自动驾驶车辆（AV）面临的一大挑战，尤其是在混合和动态交通场景中。最近，强化学习（RL）作为一种强大的数据驱动控制方法，在AVs中被广泛用于车道变更决策，并取得了令人鼓舞的结果。然而，这些研究大多集中在单一车辆设置上，并且在多个AV与人类驾驶车辆（HDV）共存的情况下的车道变换很少受到关注。在本文中，我们将混合交通公路环境中多个AV的换道决策描述为一个多智能体强化学习（MARL）问题，其中每个AV根据相邻AV和HDV的运动做出换道决策。具体地说，通过一种新颖的局部奖励设计和参数共享方案，开发了一种多智能体优势参与者-批评家网络（MA2C）。特别是，提出了一种多目标奖励函数，以综合燃油效率、驾驶舒适性和自主驾驶安全性。在三种不同交通密度和不同程度的驾驶员攻击性下进行的综合实验结果表明，我们提出的MARL框架在效率、安全性和驾驶员舒适性方面始终优于一些最先进的基准。 摘要：Autonomous driving has attracted significant research interests in the past two decades as it offers many potential benefits, including releasing drivers from exhausting driving and mitigating traffic congestion, among others. Despite promising progress, lane-changing remains a great challenge for autonomous vehicles (AV), especially in mixed and dynamic traffic scenarios. Recently, reinforcement learning (RL), a powerful data-driven control method, has been widely explored for lane-changing decision makings in AVs with encouraging results demonstrated. However, the majority of those studies are focused on a single-vehicle setting, and lane-changing in the context of multiple AVs coexisting with human-driven vehicles (HDVs) have received scarce attention. In this paper, we formulate the lane-changing decision making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs. Specifically, a multi-agent advantage actor-critic network (MA2C) is developed with a novel local reward design and a parameter sharing scheme. In particular, a multi-objective reward function is proposed to incorporate fuel efficiency, driving comfort, and safety of autonomous driving. Comprehensive experimental results, conducted under three different traffic densities and various levels of human driver aggressiveness, show that our proposed MARL framework consistently outperforms several state-of-the-art benchmarks in terms of efficiency, safety and driver comfort.

【2】 Model-Based Reinforcement Learning for Stochastic Hybrid Systems 标题：基于模型的随机混合系统强化学习 链接：https://arxiv.org/abs/2111.06211

作者：Hany Abdulsamad,Jan Peters 机构： Peters are with the Technical University ofDarmstadt 摘要：一般非线性系统的最优控制是自动化领域的一个核心挑战。由强大的函数逼近器实现的数据驱动控制方法最近在解决具有挑战性的机器人应用方面取得了巨大成功。然而，这样的方法往往掩盖了参数化表示黑盒背后的动力学和控制结构，从而限制了我们理解闭环行为的能力。本文采用非线性建模与控制的混合系统观点，为问题提供了明确的层次结构，并将复杂动力学分解为更简单的局部单元。因此，我们考虑一个序列建模范式，捕捉数据的时间结构，并导出一个期望最大化（EM）算法，自动分解非线性动力学到随机分段仿射动力系统的非线性边界。此外，我们还证明了这些时间序列模型自然地允许闭环扩展，我们通过模仿学习从非线性专家那里提取局部线性或多项式反馈控制器。最后，我们介绍了一种新的混合实时熵策略搜索（Hb-REPS）技术，该技术结合了混合系统的层次性，并优化了一组由全局值函数的局部多项式近似得到的时不变局部反馈控制器。 摘要：Optimal control of general nonlinear systems is a central challenge in automation. Data-driven approaches to control, enabled by powerful function approximators, have recently had great success in tackling challenging robotic applications. However, such methods often obscure the structure of dynamics and control behind black-box over-parameterized representations, thus limiting our ability to understand the closed-loop behavior. This paper adopts a hybrid-system view of nonlinear modeling and control that lends an explicit hierarchical structure to the problem and breaks down complex dynamics into simpler localized units. Therefore, we consider a sequence modeling paradigm that captures the temporal structure of the data and derive an expecation-maximization (EM) algorithm that automatically decomposes nonlinear dynamics into stochastic piecewise affine dynamical systems with nonlinear boundaries. Furthermore, we show that these time-series models naturally admit a closed-loop extension that we use to extract locally linear or polynomial feedback controllers from nonlinear experts via imitation learning. Finally, we introduce a novel hybrid realtive entropy policy search (Hb-REPS) technique that incorporates the hierarchical nature of hybrid systems and optimizes a set of time-invariant local feedback controllers derived from a locally polynomial approximation of a global value function.

【3】 Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control 标题：用于交互控制的最小化惊讶强化学习技术 链接：https://arxiv.org/abs/2111.06025

作者：William Arnold,Tarang Srivastava,Lucas Spangher,Utkarsha Agwan,Costas Spanos 机构：Electrical Engineering and Computer, Sciences, University of California, Berkeley 摘要：优化能源需求响应的价格需要一个能够在复杂环境中导航的灵活控制器。我们提出了一种结构修改最小的强化学习控制器。我们建议，惊喜最小化可以用来提高学习速度，利用人们能源使用的可预测性。我们的架构在能源需求响应模拟中表现良好。我们提出这种修改，以提高功能，并在大规模实验中节省。 摘要：Optimizing prices for energy demand response requires a flexible controller with ability to navigate complex environments. We propose a reinforcement learning controller with surprise minimizing modifications in its architecture. We suggest that surprise minimization can be used to improve learning speed, taking advantage of predictability in peoples' energy usage. Our architecture performs well in a simulation of energy demand response. We propose this modification to improve functionality and save in a large scale experiment.

【4】 On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning 标题：多智能体强化学习中吸收态的使用与误用 链接：https://arxiv.org/abs/2111.05992

作者：Andrew Cohen,Ervin Teng,Vincent-Pierre Berges,Ruo-Ping Dong,Hunter Henry,Marwan Mattar,Alexander Zook,Sujoy Ganguly 机构：Unity Technologies 摘要：协作式多智能体强化学习（MARL）中智能体的创建和销毁是一个关键的研究领域。当前的MARL算法通常假设在整个实验过程中，一个组中的代理数量保持不变。然而，在许多实际问题中，代理可能会在其队友之前终止。这一提前终止问题提出了一个挑战：被终止的代理必须从集团自身存在之外的成功或失败中吸取教训。我们将剩余队友获得的奖励传播给终止代理的价值称为死后信用分配问题。当前的MARL方法通过将这些试剂置于吸收状态，直到整个试剂组达到终止条件来处理此问题。虽然吸收状态使现有算法和API能够在不修改的情况下处理终止的代理，但实际的训练效率和资源使用问题仍然存在。在这项工作中，我们首先证明了在一个完全连通的网络中，样本复杂度随着玩具监督学习任务中吸收状态的数量的增加而增加，而注意力对可变大小的输入更为鲁棒。然后，我们为现有的最先进的MARL算法提出了一种新的体系结构，该算法使用注意代替具有吸收状态的完全连接层。最后，我们证明了这种新的体系结构在场景中创建或销毁代理的任务以及标准的多代理协调任务上显著优于标准体系结构。 摘要：The creation and destruction of agents in cooperative multi-agent reinforcement learning (MARL) is a critically under-explored area of research. Current MARL algorithms often assume that the number of agents within a group remains fixed throughout an experiment. However, in many practical problems, an agent may terminate before their teammates. This early termination issue presents a challenge: the terminated agent must learn from the group's success or failure which occurs beyond its own existence. We refer to propagating value from rewards earned by remaining teammates to terminated agents as the Posthumous Credit Assignment problem. Current MARL methods handle this problem by placing these agents in an absorbing state until the entire group of agents reaches a termination condition. Although absorbing states enable existing algorithms and APIs to handle terminated agents without modification, practical training efficiency and resource use problems exist. In this work, we first demonstrate that sample complexity increases with the quantity of absorbing states in a toy supervised learning task for a fully connected network, while attention is more robust to variable size input. Then, we present a novel architecture for an existing state-of-the-art MARL algorithm which uses attention instead of a fully connected layer with absorbing states. Finally, we demonstrate that this novel architecture significantly outperforms the standard architecture on tasks in which agents are created or destroyed within episodes as well as standard multi-agent coordination tasks.

【5】 PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems 标题：PowerGridWorld：一种电力系统多Agent强化学习框架 链接：https://arxiv.org/abs/2111.05969

作者：David Biagioni,Xiangyu Zhang,Dylan Wald,Deepthi Vaidhynathan,Rohit Chintala,Jennifer King,Ahmed S. Zamzam 机构： Department of Energy (DOE) under ContractNo 摘要：我们展示了PowerGridworld软件包，为用户提供了一个轻量级、模块化和可定制的框架，用于创建以电力系统为中心的多代理健身房环境，该环境可随时与现有强化学习（RL）训练框架集成。尽管存在许多用于训练多代理RL（MARL）策略的框架，但没有一个框架能够快速原型化和开发环境本身，特别是在异构（复合、多设备）电力系统的环境中，其中需要潮流解决方案来定义电网级变量和成本。PowerGridworld是一个开源软件包，有助于填补这一空白。为了突出PowerGridworld的关键功能，我们提供了两个案例研究，并演示了如何使用OpenAI的多代理深层确定性策略梯度（MADDPG）和RLLib的近端策略优化（PPO）算法学习MARL策略。在这两种情况下，至少有一些代理子集在每个时间步将潮流解决方案的元素合并为其报酬（负成本）结构的一部分。 摘要：We present the PowerGridworld software package to provide users with a lightweight, modular, and customizable framework for creating power-systems-focused, multi-agent Gym environments that readily integrate with existing training frameworks for reinforcement learning (RL). Although many frameworks exist for training multi-agent RL (MARL) policies, none can rapidly prototype and develop the environments themselves, especially in the context of heterogeneous (composite, multi-device) power systems where power flow solutions are required to define grid-level variables and costs. PowerGridworld is an open-source software package that helps to fill this gap. To highlight PowerGridworld's key features, we present two case studies and demonstrate learning MARL policies using both OpenAI's multi-agent deep deterministic policy gradient (MADDPG) and RLLib's proximal policy optimization (PPO) algorithms. In both cases, at least some subset of agents incorporates elements of the power flow solution at each time step as part of their reward (negative cost) structures.

符号|符号学习(2篇)

【1】 Towards Axiomatic, Hierarchical, and Symbolic Explanation for Deep Models 标题：深层模型的公理化、层次化和符号化解释 链接：https://arxiv.org/abs/2111.06206

作者：Jie Ren,Mingjie Li,Qihan Ren,Huiqi Deng,Quanshi Zhang 机构：a Shanghai Jiao Tong University 摘要：本文提出了一种层次符号与或图（AOG）来客观地解释由训练有素的深层推理模型编码的内部逻辑。我们首先在博弈论中定义了解释者模型的客观性，并发展了由深度模型编码的and或逻辑的严格表示。AOG解释者的客观性和可信度在理论上得到了保证，在实验上也得到了验证。此外，我们还提出了一些技巧来提高解释的简洁性。 摘要：This paper proposes a hierarchical and symbolic And-Or graph (AOG) to objectively explain the internal logic encoded by a well-trained deep model for inference. We first define the objectiveness of an explainer model in game theory, and we develop a rigorous representation of the And-Or logic encoded by the deep model. The objectiveness and trustworthiness of the AOG explainer are both theoretically guaranteed and experimentally verified. Furthermore, we propose several techniques to boost the conciseness of the explanation.

【2】 A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations 标题：超维计算(又称矢量符号体系结构)综述(一)：模型与数据转换 链接：https://arxiv.org/abs/2111.06077

作者：Denis Kleyko,Dmitri A. Rachkovskij,Evgeny Osipov,Abbas Rahimi 机构：! 备注：27 pages 摘要：这个由两部分组成的综合调查致力于一个计算框架，这个框架最常见的名称是超维计算和向量符号体系结构（HDC/VSA）。这两个名称都是指一系列计算模型，这些模型使用高维分布式表示，并依赖其关键操作的代数特性来结合结构化符号表示和向量分布式表示的优点。HDC/VSA系列中值得注意的模型有张量积表示、全息约化表示、乘加置换、二进制飞溅码和稀疏二进制分布表示，但也有其他模型。HDC/VSA是一个高度跨学科的领域，与计算机科学、电气工程、人工智能、数学和认知科学密切相关。这一事实使得对该地区进行全面的概述具有挑战性。然而，由于近年来加入该地区的新研究人员激增，对该地区进行全面调查的必要性变得极其重要。因此，在该领域的其他方面中，本第I部分调查了重要方面，例如：HDC/VSA的已知计算模型以及各种输入数据类型到高维分布式表示的转换。本调查的第二部分致力于应用程序、认知计算和体系结构，以及未来工作的方向。这项调查对新手和从业者都很有用。 摘要：This two-part comprehensive survey is devoted to a computing framework most commonly known under the names Hyperdimensional Computing and Vector Symbolic Architectures (HDC/VSA). Both names refer to a family of computational models that use high-dimensional distributed representations and rely on the algebraic properties of their key operations to incorporate the advantages of structured symbolic representations and vector distributed representations. Notable models in the HDC/VSA family are Tensor Product Representations, Holographic Reduced Representations, Multiply-Add-Permute, Binary Spatter Codes, and Sparse Binary Distributed Representations but there are other models too. HDC/VSA is a highly interdisciplinary area with connections to computer science, electrical engineering, artificial intelligence, mathematics, and cognitive science. This fact makes it challenging to create a thorough overview of the area. However, due to a surge of new researchers joining the area in recent years, the necessity for a comprehensive survey of the area has become extremely important. Therefore, amongst other aspects of the area, this Part I surveys important aspects such as: known computational models of HDC/VSA and transformations of various input data types to high-dimensional distributed representations. Part II of this survey is devoted to applications, cognitive computing and architectures, as well as directions for future work. The survey is written to be useful for both newcomers and practitioners.

医学相关(4篇)

【1】 Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes 标题：灵活调整临床结果的电子健康记录纵向患者分层 链接：https://arxiv.org/abs/2111.06152

作者：Oliver Carr,Avelino Javer,Patrick Rockenschaub,Owen Parsons,Robert Dürichen 机构：Robert D¨urichen, Sensyne Health Plc, Oxford, UK 备注：12 pages, 2 figures (excluding appendix) Accepted to Machine Learning for Health (ML4H) 2021 摘要：纵向电子健康记录（EHR）数据可用性的增加导致对疾病的更好理解和新表型的发现。大多数聚类算法只关注患者的轨迹，但具有相似轨迹的患者可能会有不同的结果。发现具有不同轨迹和结果的患者亚组可以指导未来的药物开发，并改善临床试验的招募。我们开发了一个递归神经网络自动编码器，使用重建、结果和聚类损失对EHR数据进行聚类，这些数据可以加权以找到不同类型的患者聚类。我们表明，我们的模型能够从数据偏差和结果差异中发现已知的聚类，优于基线模型。我们在29229美元的糖尿病患者身上演示了该模型的性能，表明它发现了具有不同轨迹和不同结果的患者群，可用于帮助临床决策。 摘要：The increase in availability of longitudinal electronic health record (EHR) data is leading to improved understanding of diseases and discovery of novel phenotypes. The majority of clustering algorithms focus only on patient trajectories, yet patients with similar trajectories may have different outcomes. Finding subgroups of patients with different trajectories and outcomes can guide future drug development and improve recruitment to clinical trials. We develop a recurrent neural network autoencoder to cluster EHR data using reconstruction, outcome, and clustering losses which can be weighted to find different types of patient clusters. We show our model is able to discover known clusters from both data biases and outcome differences, outperforming baseline models. We demonstrate the model performance on $29,229$ diabetes patients, showing it finds clusters of patients with both different trajectories and different outcomes which can be utilized to aid clinical decision making.

【2】 Kronecker Factorization for Preventing Catastrophic Forgetting in Large-scale Medical Entity Linking 标题：防止大规模医疗实体链接中灾难性遗忘的Kronecker因子分解 链接：https://arxiv.org/abs/2111.06012

作者：Denis Jered McInerney,Luyang Kong,Kristjan Arumae,Byron Wallace,Parminder Bhatia 机构：Northeastern University, Amazon AI, Qualtrics 摘要：多任务学习在NLP中很有用，因为通常需要一个跨一系列任务的单一模型。在医学领域，任务顺序训练有时可能是训练模型的唯一方法，因为无法再访问原始（潜在敏感）数据，或者仅仅是因为联合再训练固有的计算成本。然而，顺序学习固有的一个主要问题是灾难性遗忘，即，当为新任务更新模型时，先前任务的准确度大幅下降。弹性权重固结是最近提出的一种解决这一问题的方法，但将这种方法扩展到实践中使用的现代大型模型需要对模型参数做出强烈的独立假设，从而限制了其有效性。在这项工作中，我们应用Kronecker因子分解——一种放松独立性假设的最新方法——在卷积神经网络和基于Transformer的神经网络中防止大规模的灾难性遗忘。我们展示了该技术在跨三个数据集的医疗实体链接这一重要和说明性任务中的有效性，展示了该技术在新的医疗数据可用时对现有方法进行有效更新的能力。平均而言，当使用基于BERT的模型时，所提出的方法将灾难性遗忘减少了51%，而使用标准弹性权重合并时，灾难性遗忘减少了27%，同时保持了与模型参数数量成比例的空间复杂度。 摘要：Multi-task learning is useful in NLP because it is often practically desirable to have a single model that works across a range of tasks. In the medical domain, sequential training on tasks may sometimes be the only way to train models, either because access to the original (potentially sensitive) data is no longer available, or simply owing to the computational costs inherent to joint retraining. A major issue inherent to sequential learning, however, is catastrophic forgetting, i.e., a substantial drop in accuracy on prior tasks when a model is updated for a new task. Elastic Weight Consolidation is a recently proposed method to address this issue, but scaling this approach to the modern large models used in practice requires making strong independence assumptions about model parameters, limiting its effectiveness. In this work, we apply Kronecker Factorization--a recent approach that relaxes independence assumptions--to prevent catastrophic forgetting in convolutional and Transformer-based neural networks at scale. We show the effectiveness of this technique on the important and illustrative task of medical entity linking across three datasets, demonstrating the capability of the technique to be used to make efficient updates to existing methods as new medical data becomes available. On average, the proposed method reduces catastrophic forgetting by 51% when using a BERT-based model, compared to a 27% reduction using standard Elastic Weight Consolidation, while maintaining spatial complexity proportional to the number of model parameters.

【3】 A Generic Deep Learning Based Cough Analysis System from Clinically Validated Samples for Point-of-Need Covid-19 Test and Severity Levels 标题：一种基于深度学习的通用咳嗽分析系统，用于需要点冠状病毒检测和严重程度的临床验证样本 链接：https://arxiv.org/abs/2111.05895

作者：Javier Andreu-Perez,Humberto Pérez-Espinosa,Eva Timonet,Mehrin Kiani,Manuel I. Girón-Pérez,Alma B. Benitez-Trinidad,Delaram Jarchi,Alejandro Rosales-Pérez,Nick Gatzoulis,Orion F. Reyes-Galaviz,Alejandro Torres-García,Carlos A. Reyes-García,Zulfiqar Ali,Francisco Rivas 备注：None 摘要：我们试图通过实验室分子测试（2339例Covid-19阳性和6041例Covid-19阴性）对8380份经临床验证的样本的咳嗽声，评估快速初步筛选Covid-19工具的检测性能。根据定量RT-PCR（qRT-PCR）分析、周期阈值和患者淋巴细胞计数，根据结果和严重程度对样本进行临床标记。我们提出的通用方法是一种基于经验模式分解（EMD）的算法，随后基于音频特征张量进行分类，以及一种称为DeepCough'的具有卷积层的深度人工神经网络分类器。研究了基于张量维数的两种不同版本的DeepCough，即DeepCough 2D和DeepCough 3D。这些方法已部署在多平台概念验证Web应用程序中，用于匿名管理此测试。对于三种严重程度的识别，Covid-19识别结果率的AUC（曲线下面积）为98.800.83%，敏感性为96.431.85%，特异性为96.201.74%，AUC为81.08%5.05%。我们提出的用于鲁棒、快速、需要点识别新冠病毒19的网络工具和基础算法有助于快速检测感染。我们认为，它有可能在全世界范围内严重阻碍新冠病毒-19的流行。 摘要：We seek to evaluate the detection performance of a rapid primary screening tool of Covid-19 solely based on the cough sound from 8,380 clinically validated samples with laboratory molecular-test (2,339 Covid-19 positives and 6,041 Covid-19 negatives). Samples were clinically labeled according to the results and severity based on quantitative RT-PCR (qRT-PCR) analysis, cycle threshold, and lymphocytes count from the patients. Our proposed generic method is an algorithm based on Empirical Mode Decomposition (EMD) with subsequent classification based on a tensor of audio features and a deep artificial neural network classifier with convolutional layers called DeepCough'. Two different versions of DeepCough based on the number of tensor dimensions, i.e. DeepCough2D and DeepCough3D, have been investigated. These methods have been deployed in a multi-platform proof-of-concept Web App CoughDetect to administer this test anonymously. Covid-19 recognition results rates achieved a promising AUC (Area Under Curve) of 98.800.83%, sensitivity of 96.431.85%, and specificity of 96.201.74%, and 81.08%5.05% AUC for the recognition of three severity levels. Our proposed web tool and underpinning algorithm for the robust, fast, point-of-need identification of Covid-19 facilitates the rapid detection of the infection. We believe that it has the potential to significantly hamper the Covid-19 pandemic across the world.

【4】 Detecting COVID-19 from Chest Computed Tomography Scans using AI-Driven Android Application 标题：使用人工智能驱动的Android应用从胸部CT扫描中检测冠状病毒 链接：https://arxiv.org/abs/2111.06254

作者：Aryan Verma,Sagar B. Amin,Muhammad Naeem,Monjoy Saha 摘要：到2021年6月，新冠病毒-19（2019年冠状病毒病）大流行影响了全球1.86亿人，死亡人数超过400万。其严重程度已使全球医疗体系陷入紧张。胸部计算机断层扫描（CT）在新冠病毒-19的诊断和预测中具有潜在的作用。设计一个经济高效且便于在手机等资源有限的设备上操作的诊断系统将提高胸部CT扫描的临床使用率，并提供快速、移动和可访问的诊断功能。这项工作建议开发一种新的Android应用程序，使用高效准确的深度学习算法从胸部CT扫描中检测新冠病毒-19感染。它进一步创建了一个注意力热图，通过作为本工作一部分开发的算法在CT扫描中的肺实质分割区域增强，该算法显示了肺部感染区域。我们提出了一种结合多线程的选择方法，可以在Android设备上更快地生成热图，从而将处理时间减少约93%。本研究中训练用于检测新冠病毒-19的神经网络的F1评分和准确率均为99.58%，灵敏度为99.69%，优于CT扫描诊断新冠病毒领域的大多数结果。这项工作将有助于大量实践，并帮助医生快速有效地对患者进行分类，以早期诊断新冠病毒-19。 摘要：The COVID-19 (coronavirus disease 2019) pandemic affected more than 186 million people with over 4 million deaths worldwide by June 2021. The magnitude of which has strained global healthcare systems. Chest Computed Tomography (CT) scans have a potential role in the diagnosis and prognostication of COVID-19. Designing a diagnostic system which is cost-efficient and convenient to operate on resource-constrained devices like mobile phones would enhance the clinical usage of chest CT scans and provide swift, mobile, and accessible diagnostic capabilities. This work proposes developing a novel Android application that detects COVID-19 infection from chest CT scans using a highly efficient and accurate deep learning algorithm. It further creates an attention heatmap, augmented on the segmented lung parenchyma region in the CT scans through an algorithm developed as a part of this work, which shows the regions of infection in the lungs. We propose a selection approach combined with multi-threading for a faster generation of heatmaps on Android Device, which reduces the processing time by about 93%. The neural network trained to detect COVID-19 in this work is tested with F1 score and accuracy, both of 99.58% and sensitivity of 99.69%, which is better than most of the results in the domain of COVID diagnosis from CT scans. This work will be beneficial in high volume practices and help doctors triage patients in the early diagnosis of the COVID-19 quickly and efficiently.

蒸馏|知识提取(2篇)

【1】 Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation 标题：面向机器人操作的运动规划器增广策略提取与视觉控制策略 链接：https://arxiv.org/abs/2111.06383

作者：I-Chun Arthur Liu,Shagun Uppal,Gaurav S. Sukhatme,Joseph J. Lim,Peter Englert,Youngwoon Lee 机构：Cognitive Learning for Vision and Robotics Lab, Robotic Embedded Systems Laboratory, University of Southern California 备注：Published at the Conference on Robot Learning (CoRL) 2021 摘要：在现实的、有障碍的环境中学习复杂的操作任务是一个具有挑战性的问题，因为在存在障碍物和高维视觉观察的情况下进行了艰苦的探索。之前的工作通过整合运动规划和强化学习来解决探索问题。但是，motion planner增强策略需要访问状态信息，这在现实环境中通常不可用。为此，我们建议通过（1）视觉行为克隆将基于状态的运动规划器增强策略提取为视觉控制策略，以消除运动规划器依赖性及其抖动的运动，（2）在行为克隆代理的平滑轨迹指导下基于视觉的强化学习。我们评估了我们的方法在障碍环境中的三个操作任务，并将其与各种强化学习和模仿学习基线进行比较。结果表明，我们的框架具有很高的样本效率，并且优于最新的算法。此外，再加上区域随机化，我们的策略能够在有干扰物的情况下将Zero-Shot转移到看不见的环境中。代码和视频可在https://clvrai.com/mopa-pd 摘要：Learning complex manipulation tasks in realistic, obstructed environments is a challenging problem due to hard exploration in the presence of obstacles and high-dimensional visual observations. Prior work tackles the exploration problem by integrating motion planning and reinforcement learning. However, the motion planner augmented policy requires access to state information, which is often not available in the real-world settings. To this end, we propose to distill a state-based motion planner augmented policy to a visual control policy via (1) visual behavioral cloning to remove the motion planner dependency along with its jittery motion, and (2) vision-based reinforcement learning with the guidance of the smoothed trajectories from the behavioral cloning agent. We evaluate our method on three manipulation tasks in obstructed environments and compare it against various reinforcement learning and imitation learning baselines. The results demonstrate that our framework is highly sample-efficient and outperforms the state-of-the-art algorithms. Moreover, coupled with domain randomization, our policy is capable of zero-shot transfer to unseen environment settings with distractors. Code and videos are available at https://clvrai.com/mopa-pd

【2】 Keys to Accurate Feature Extraction Using Residual Spiking Neural Networks 标题：利用残差尖峰神经网络进行精确特征提取的关键 链接：https://arxiv.org/abs/2111.05955

作者：Alex Vicente-Sola,Davide L. Manna,Paul Kirkland,Gaetano Di Caterina,Trevor Bihl 机构： University ofStrathclyde 备注：13 pages, 5 figures, 14 tables 摘要：尖峰神经网络（SNN）已成为传统人工神经网络（ANN）的一种有趣的替代方案，这得益于其时间处理能力以及在神经形态硬件中的低交换（大小、重量和功率）和节能实现。然而，训练SNN所涉及的挑战限制了它们在准确性方面的性能，从而限制了它们的应用。因此，改进学习算法和神经网络结构以获得更精确的特征提取是当前SNN研究的重点之一。在这篇文章中，我们对现代扣球体系结构的关键组件进行了研究。我们对从性能最好的网络中获取的图像分类数据集中的不同技术进行了经验比较。我们设计了一个成功剩余网络（ResNet）体系结构的尖峰版本，并在其上测试了不同的组件和训练策略。我们的研究结果为SNN设计提供了最先进的指导，在尝试构建最佳视觉特征提取器时，可以做出明智的选择。最后，我们的网络在CIFAR-10（94.1%）和CIFAR-100（74.5%）数据集中的性能优于以前的SNN体系结构，并与DVS-CIFAR10（71.3%）中的最新技术相匹配，参数比以前的最新技术更少，并且不需要ANN-SNN转换。代码可在https://github.com/VicenteAlex/Spiking_ResNet. 摘要：Spiking neural networks (SNNs) have become an interesting alternative to conventional artificial neural networks (ANN) thanks to their temporal processing capabilities and their low-SWaP (Size, Weight, and Power) and energy efficient implementations in neuromorphic hardware. However the challenges involved in training SNNs have limited their performance in terms of accuracy and thus their applications. Improving learning algorithms and neural architectures for a more accurate feature extraction is therefore one of the current priorities in SNN research. In this paper we present a study on the key components of modern spiking architectures. We empirically compare different techniques in image classification datasets taken from the best performing networks. We design a spiking version of the successful residual network (ResNet) architecture and test different components and training strategies on it. Our results provide a state of the art guide to SNN design, which allows to make informed choices when trying to build the optimal visual feature extractor. Finally, our network outperforms previous SNN architectures in CIFAR-10 (94.1%) and CIFAR-100 (74.5%) datasets and matches the state of the art in DVS-CIFAR10 (71.3%), with less parameters than the previous state of the art and without the need for ANN-SNN conversion. Code available at https://github.com/VicenteAlex/Spiking_ResNet.

联邦学习|隐私保护|加密(1篇)

【1】 FedGreen: Federated Learning with Fine-Grained Gradient Compression for Green Mobile Edge Computing 标题：FedGreen：面向绿色移动边缘计算的细粒度梯度压缩联合学习 链接：https://arxiv.org/abs/2111.06146

作者：Peichun Li,Xumin Huang,Miao Pan,Rong Yu 机构：∗School of Automation, Guangdong University of Technology, Guangzhou, China, †Department of Electrical and Computer Engineering, University of Houston, Houston, USA 备注：Accepted for publication in Globecom'21 摘要：联邦学习（FL）使移动边缘计算（MEC）中的设备能够协作训练共享模型，而无需上传本地数据。梯度压缩可以应用于FL以减轻通信开销，但是当前具有梯度压缩的FL仍然面临巨大挑战。为了部署绿色MEC，我们提出了FedGreen，它通过细粒度梯度压缩来增强原始FL，从而有效地控制设备的总能耗。具体来说，我们引入了相关操作，包括设备端梯度减少和服务器端元素聚合，以促进FL中的梯度压缩。根据一个公共数据集，我们研究了压缩的局部梯度对不同压缩比的贡献。在此基础上，我们提出并解决了一个学习精度和能量效率的折衷问题，其中每个设备的最佳压缩比和计算频率都是推导出来的。实验结果表明，在80%的测试精度要求下，与基线方案相比，FedGreen至少降低了设备总能耗的32%。 摘要：Federated learning (FL) enables devices in mobile edge computing (MEC) to collaboratively train a shared model without uploading the local data. Gradient compression may be applied to FL to alleviate the communication overheads but current FL with gradient compression still faces great challenges. To deploy green MEC, we propose FedGreen, which enhances the original FL with fine-grained gradient compression to efficiently control the total energy consumption of the devices. Specifically, we introduce the relevant operations including device-side gradient reduction and server-side element-wise aggregation to facilitate the gradient compression in FL. According to a public dataset, we investigate the contributions of the compressed local gradients with respect to different compression ratios. After that, we formulate and tackle a learning accuracy-energy efficiency tradeoff problem where the optimal compression ratio and computing frequency are derived for each device. Experiments results demonstrate that given the 80% test accuracy requirement, compared with the baseline schemes, FedGreen reduces at least 32% of the total energy consumption of the devices.

推理|分析|理解|解释(3篇)

【1】 Understanding mobility in networks: A node embedding approach 标题：了解网络中的移动性：一种节点嵌入方法 链接：https://arxiv.org/abs/2111.06161

作者：Matheus F. C. Barros,Carlos H. G. Ferreira,Bruno Pereira dos Santos,Lourenço A. P. Júnior,Marco Mellia,Jussara M. Almeida 机构：Universidade Federal de Ouro Preto, Universidade Federal de Minas Gerais, Politecnico di Torino, Lourenc¸o A. P. J´unior, Instituto Tecnol´ogico de Aeron´autica 摘要：受能够连接和交换消息的移动设备数量不断增加的推动，我们提出了一种旨在建模和分析网络中节点移动性的方法。我们注意到，文献中的许多现有解决方案依赖于直接在节点接触图上计算的拓扑测量，旨在捕捉节点在连通性和移动性模式方面的重要性，这有利于移动网络的原型设计、设计和部署。然而，每种度量都有其特殊性，无法概括最终随时间变化的节点重要性概念。与以前的方法不同，我们的方法基于一种节点嵌入方法，该方法建模并揭示节点在移动性和连通性模式中的重要性，同时保留其空间和时间特征。我们将重点放在基于小组会议痕迹的案例研究上。结果表明，我们的方法为提取不同的移动性和连接性模式提供了丰富的表示，这有助于移动网络中的各种应用和服务。 摘要：Motivated by the growing number of mobile devices capable of connecting and exchanging messages, we propose a methodology aiming to model and analyze node mobility in networks. We note that many existing solutions in the literature rely on topological measurements calculated directly on the graph of node contacts, aiming to capture the notion of the node's importance in terms of connectivity and mobility patterns beneficial for prototyping, design, and deployment of mobile networks. However, each measure has its specificity and fails to generalize the node importance notions that ultimately change over time. Unlike previous approaches, our methodology is based on a node embedding method that models and unveils the nodes' importance in mobility and connectivity patterns while preserving their spatial and temporal characteristics. We focus on a case study based on a trace of group meetings. The results show that our methodology provides a rich representation for extracting different mobility and connectivity patterns, which can be helpful for various applications and services in mobile networks.

【2】 Fine-Grained Image Analysis with Deep Learning: A Survey 标题：基于深度学习的细粒度图像分析研究综述 链接：https://arxiv.org/abs/2111.06119

作者：Xiu-Shen Wei,Yi-Zhe Song,Oisin Mac Aodha,Jianxin Wu,Yuxin Peng,Jinhui Tang,Jian Yang,Serge Belongie 机构： Song is with University of Surrey, Mac Aodha is with the University ofEdinburgh, Nanjing University, Peng is with Peking University 备注：Accepted by IEEE TPAMI 摘要：细粒度图像分析（FGIA）是计算机视觉和模式识别中一个长期存在的基本问题，是各种实际应用的基础。FGIA的任务是分析来自从属类别的视觉对象，例如鸟类物种或汽车模型。细粒度图像分析固有的小类间和大类内变化使其成为一个具有挑战性的问题。利用深度学习的进步，近年来我们见证了以深度学习为动力的FGIA的显著进步。在本文中，我们对这些进展进行了系统的综述，试图通过整合两个基本的细粒度研究领域——细粒度图像识别和细粒度图像检索，重新定义和拓宽FGIA领域。此外，我们还回顾了FGIA的其他关键问题，如公开的基准数据集和相关的领域特定应用程序。最后，我们强调了一些需要社区进一步探索的研究方向和开放性问题。 摘要：Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from subordinate categories, e.g., species of birds or models of cars. The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem. Capitalizing on advances in deep learning, in recent years we have witnessed remarkable progress in deep learning powered FGIA. In this paper we present a systematic survey of these advances, where we attempt to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas -- fine-grained image recognition and fine-grained image retrieval. In addition, we also review other key issues of FGIA, such as publicly available benchmark datasets and related domain-specific applications. We conclude by highlighting several research directions and open problems which need further exploration from the community.

【3】 Towards Theoretical Understanding of Flexible Transmitter Networks via Approximation and Local Minima 标题：基于近似和局部极小的柔性发射机网络的理论理解 链接：https://arxiv.org/abs/2111.06027

作者：Jin-Hui Wu,Shao-Qun Zhang,Yuan Jiang,Zhi-Hua Zhou 机构：National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing , China 摘要：柔性传送器网络（FTNet）是最近提出的一种生物似然神经网络，在处理时空数据时，与最先进的模型相比，其性能具有竞争力。然而，关于FTNet的理论理解仍然存在一个开放的问题。本文从近似和局部极小的角度研究了单隐层FTNet的理论性质。在温和的假设下，我们证明：i）FTNet是一个普适逼近器；ii）FTNet的近似复杂度可以指数地小于具有前馈/递归结构的实值神经网络的近似复杂度，并且在最坏情况下具有相同的阶数；iii）FTNet的任何局部最小值都是全局最小值，这表明局部搜索算法有可能收敛到全局最小值。我们的理论结果表明，FTNet能够有效地表达目标函数，并且不考虑局部极小值，这补充了FTNet的理论空白，展示了改进FTNet的可能性。 摘要：Flexible Transmitter Network (FTNet) is a recently proposed bio-plausible neural network and has achieved competitive performance with the state-of-the-art models when handling temporal-spatial data. However, there remains an open problem about the theoretical understanding of FTNet. This work investigates the theoretical properties of one-hidden-layer FTNet from the perspectives of approximation and local minima. Under mild assumptions, we show that: i) FTNet is a universal approximator; ii) the approximation complexity of FTNet can be exponentially smaller than those of real-valued neural networks with feedforward/recurrent architectures and is of the same order in the worst case; iii) any local minimum of FTNet is the global minimum, which suggests that it is possible for local search algorithms to converge to the global minimum. Our theoretical results indicate that FTNet can efficiently express target functions and has no concern about local minima, which complements the theoretical blank of FTNet and exhibits the possibility for ameliorating the FTNet.

检测相关(3篇)

【1】 Improving Novelty Detection using the Reconstructions of Nearest Neighbours 标题：利用最近邻域重构改进新颖性检测 链接：https://arxiv.org/abs/2111.06150

作者：Michael Mesarcik,Elena Ranguelova,Albert-Jan Boonstra,Rob V. van Nieuwpoort 机构：University of Amsterdam, Science Park , Amsterdam,XH,the Netherlands, beScience Center, Science Park , Amsterdam,XG, the Netherlands, ASTRON, the Netherlands Institute for Radio Astronomy, Oude Hoogeveensedijk , Dwingeloo,PD, the Netherlands 摘要：我们发现，在自动编码器（AE）的潜在空间中使用最近邻显著提高了单类和多类上下文中半监督新颖性检测的性能。自动编码方法通过学习区分非新颖的训练课程和所有其他看不见的课程来检测新奇性。我们的方法利用了对给定输入的潜在表示的最近邻和潜在邻距离的重构的组合。我们证明了我们的最近潜在邻居（NLN）算法具有内存和时间效率，不需要显著的数据扩充，也不依赖于预先训练的网络。此外，我们还证明了NLN算法在无需修改的情况下很容易适用于多个数据集。此外，该算法与自动编码器结构和重构误差方法无关。我们使用重建、残差或特征一致性损失，在多个标准数据集上验证了我们的方法，用于各种不同的自动编码体系结构，如普通、对抗和可变自动编码器。结果表明，对于多类情况，NLN算法在接收机工作特性（AUROC）曲线下的面积性能提高了17%，而对于单类新颖性检测，NLN算法的面积性能提高了8%。 摘要：We show that using nearest neighbours in the latent space of autoencoders (AE) significantly improves performance of semi-supervised novelty detection in both single and multi-class contexts. Autoencoding methods detect novelty by learning to differentiate between the non-novel training class(es) and all other unseen classes. Our method harnesses a combination of the reconstructions of the nearest neighbours and the latent-neighbour distances of a given input's latent representation. We demonstrate that our nearest-latent-neighbours (NLN) algorithm is memory and time efficient, does not require significant data augmentation, nor is reliant on pre-trained networks. Furthermore, we show that the NLN-algorithm is easily applicable to multiple datasets without modification. Additionally, the proposed algorithm is agnostic to autoencoder architecture and reconstruction error method. We validate our method across several standard datasets for a variety of different autoencoding architectures such as vanilla, adversarial and variational autoencoders using either reconstruction, residual or feature consistent losses. The results show that the NLN algorithm grants up to a 17% increase in Area Under the Receiver Operating Characteristics (AUROC) curve performance for the multi-class case and 8% for single-class novelty detection.

【2】 Exploiting the Power of Levenberg-Marquardt Optimizer with Anomaly Detection in Time Series 标题：利用时间序列异常检测发挥Levenberg-MarQuardt优化器的作用 链接：https://arxiv.org/abs/2111.06060

作者：Wenyi Wang,John Taylor,Biswajit Bala 机构：Defence Science and Technology Group, Australia, CSIRO, Data, Australia, Australian National University, School of Computing 备注：8 pages, 9 figures, unpublished manuscript 摘要：Levenberg-Marquardt（LM）优化算法已广泛用于解决机器学习问题。文献综述表明，当网络中的权重数不超过几百个时，LM可以非常有效地处理中等函数近似问题。相比之下，LM在处理模式识别或分类问题时表现不佳，在网络变大（例如，权重超过500）时效率低下。在本文中，我们使用一些真实世界的飞机数据集来开发LM算法的真正威力。在这些数据集上，大多数其他常用的优化器无法检测由飞机发动机条件变化引起的异常。数据集的挑战性在于时间序列数据的突变。我们发现LM优化器比其他优化器具有更好的逼近突变和检测异常的能力。我们比较了LM和其他几个优化器在解决此异常/更改检测问题时的性能。我们根据一系列措施评估相对性能，包括网络复杂性（即权重数量）、拟合精度、过度拟合、训练时间、，使用GPU和内存需求等。我们还讨论了在MATLAB和Tensorflow中实现鲁棒LM的问题，以促进LM算法的更广泛使用，以及LM优化器在大规模问题中的潜在用途。 摘要：The Levenberg-Marquardt (LM) optimization algorithm has been widely used for solving machine learning problems. Literature reviews have shown that the LM can be very powerful and effective on moderate function approximation problems when the number of weights in the network is not more than a couple of hundred. In contrast, the LM does not seem to perform as well when dealing with pattern recognition or classification problems, and inefficient when networks become large (e.g. with more than 500 weights). In this paper, we exploit the true power of LM algorithm using some real world aircraft datasets. On these datasets most other commonly used optimizers are unable to detect the anomalies caused by the changing conditions of the aircraft engine. The challenging nature of the datasets are the abrupt changes in the time series data. We find that the LM optimizer has a much better ability to approximate abrupt changes and detect anomalies than other optimizers. We compare the performance, in addressing this anomaly/change detection problem, of the LM and several other optimizers. We assess the relative performance based on a range of measures including network complexity (i.e. number of weights), fitting accuracy, over fitting, training time, use of GPUs and memory requirement etc. We also discuss the issue of robust LM implementation in MATLAB and Tensorflow for promoting more popular usage of the LM algorithm and potential use of LM optimizer for large-scale problems.

【3】 Detecting Fake Points of Interest from Location Data 标题：从位置数据中检测虚假兴趣点 链接：https://arxiv.org/abs/2111.06003

作者：Syed Raza Bashir,Vojislav Misic 机构：Department of Computer Science, Ryerson University, Toronto, Canada 备注：Accepted in IEEE 摘要：支持GPS的移动设备的普及和基于位置的服务的广泛使用导致了大量地理标记数据的产生。最近，数据分析可以访问更多的来源，包括评论、新闻和图像，这也对兴趣点（POI）数据源的可靠性提出了疑问。虽然先前的研究试图通过各种安全机制检测假POI数据，但当前的工作试图以更简单的方式捕获假POI数据。本文主要研究有监督学习方法及其在基于位置的数据中发现隐藏模式的能力。地面真值标签是通过真实数据获得的，而假数据是通过API生成的，因此我们得到了一个位置数据上同时包含真值和假值标签的数据集。目标是使用多层感知器（MLP）方法预测POI的真实性。在本文的工作中，基于数据分类技术的MLP被用来准确地分类定位数据。将该方法与传统的分类方法、稳健的深度神经网络方法和最新的深度神经网络方法进行了比较。结果表明，该方法优于基线方法。 摘要：The pervasiveness of GPS-enabled mobile devices and the widespread use of location-based services have resulted in the generation of massive amounts of geo-tagged data. In recent times, the data analysis now has access to more sources, including reviews, news, and images, which also raises questions about the reliability of Point-of-Interest (POI) data sources. While previous research attempted to detect fake POI data through various security mechanisms, the current work attempts to capture the fake POI data in a much simpler way. The proposed work is focused on supervised learning methods and their capability to find hidden patterns in location-based data. The ground truth labels are obtained through real-world data, and the fake data is generated using an API, so we get a dataset with both the real and fake labels on the location data. The objective is to predict the truth about a POI using the Multi-Layer Perceptron (MLP) method. In the proposed work, MLP based on data classification technique is used to classify location data accurately. The proposed method is compared with traditional classification and robust and recent deep neural methods. The results show that the proposed method is better than the baseline methods.

分类|识别(6篇)

【1】 Identification of Fine-Grained Location Mentions in Crisis Tweets 标题：危机推文中细粒度位置提及的识别 链接：https://arxiv.org/abs/2111.06334

作者：Sarthak Khanal,Maria Traskowsky,Doina Caragea 机构：Kansas State University 摘要：在将从社交媒体提取的态势感知信息转化为可操作信息的过程中，识别危机推文中提到的细粒度位置至关重要。大多数以前的工作都集中于识别一般位置，而不考虑其具体类型。为了促进细粒度位置识别任务的进展，我们组装了两个tweet危机数据集，并用特定的位置类型对它们进行手动注释。第一个数据集包含一组混合危机事件的推文，而第二个数据集包含全球新冠病毒-19大流行的推文。我们研究了在领域内和跨领域设置中，用于序列标记的最新深度学习模型在这些数据集上的性能。 摘要：Identification of fine-grained location mentions in crisis tweets is central in transforming situational awareness information extracted from social media into actionable information. Most prior works have focused on identifying generic locations, without considering their specific types. To facilitate progress on the fine-grained location identification task, we assemble two tweet crisis datasets and manually annotate them with specific location types. The first dataset contains tweets from a mixed set of crisis events, while the second dataset contains tweets from the global COVID-19 pandemic. We investigate the performance of state-of-the-art deep learning models for sequence tagging on these datasets, in both in-domain and cross-domain settings.

【2】 Towards an Efficient Voice Identification Using Wav2Vec2.0 and HuBERT Based on the Quran Reciters Dataset 标题：基于“古兰经”朗诵数据集的Wav2Vec2.0和Hubert语音识别 链接：https://arxiv.org/abs/2111.06331

作者：Aly Moustafa,Salah A. Aly 机构： Helwan University, Fayoum University 备注：5 pages, 9 figures, 2 tables 摘要：当前的身份验证和可信系统依赖于经典和生物特征识别方法来识别或授权用户。这些方法包括语音识别、眼睛和手指签名。最近的工具利用深度学习和Transformer来实现更好的结果。在本文中，我们利用Wav2Vec2.0和HuBERT音频表示学习工具开发了一个用于阿拉伯语说话人识别的深度学习构造模型。端到端Wav2Vec2.0范式通过随机屏蔽一组特征向量来获取上下文化语音表示学习，然后应用Transformer神经网络。我们使用了一个MLP分类器，它能够区分不变的标记类。我们给出了一些实验结果，保证了所提出模型的高精度。实验结果表明，在Wav2Vec2.0和HuBERT两种情况下，可以分别以98%和97.1%的准确率识别特定说话人的任意波形信号。 摘要：Current authentication and trusted systems depend on classical and biometric methods to recognize or authorize users. Such methods include audio speech recognitions, eye, and finger signatures. Recent tools utilize deep learning and transformers to achieve better results. In this paper, we develop a deep learning constructed model for Arabic speakers identification by using Wav2Vec2.0 and HuBERT audio representation learning tools. The end-to-end Wav2Vec2.0 paradigm acquires contextualized speech representations learnings by randomly masking a set of feature vectors, and then applies a transformer neural network. We employ an MLP classifier that is able to differentiate between invariant labeled classes. We show several experimental results that safeguard the high accuracy of the proposed model. The experiments ensure that an arbitrary wave signal for a certain speaker can be identified with 98% and 97.1% accuracies in the cases of Wav2Vec2.0 and HuBERT, respectively.

【3】 Towards Domain-Independent and Real-Time Gesture Recognition Using mmWave Signal 标题：基于毫米波信号的独立于域的实时手势识别 链接：https://arxiv.org/abs/2111.06195

作者：Yadong Li,Dongheng Zhang,Jinbo Chen,Jinwei Wan,Dong Zhang,Yang Hu,Qibin Sun,Yan Chen 备注：The paper is submitted to the journal of IEEE Transactions on Mobile Computing. And it is still under review 摘要：使用毫米波（mmWave）信号的人体手势识别提供了有吸引力的应用，包括智能家居和车内接口。虽然现有工作在受控环境下取得了良好的性能，但由于需要密集的数据收集、适应新领域（即环境、人员和位置）时的额外训练工作以及实时识别性能差，实际应用仍然受到限制。在本文中，我们提出了DI手势，一个独立于领域的实时毫米波手势识别系统。具体来说，我们首先通过时空处理推导出与人类手势相对应的信号变化。为了增强系统的鲁棒性和减少数据收集工作，我们设计了一个基于信号模式和手势变化之间相关性的数据增强框架。此外，我们还提出了一种动态窗口机制来自动准确地进行手势分割，从而实现实时识别。最后，我们构建了一个轻量级的神经网络，从数据中提取时空信息进行手势分类。大量实验结果表明，对于新用户、新环境和新位置，DI手势的平均准确率分别为97.92%、99.18%和98.76%。在实时场景中，DI-Gesutre的准确率达到97%以上，平均推理时间为2.87ms，这表明我们的系统具有优越的鲁棒性和有效性。 摘要：Human gesture recognition using millimeter wave (mmWave) signals provides attractive applications including smart home and in-car interface. While existing works achieve promising performance under controlled settings, practical applications are still limited due to the need of intensive data collection, extra training efforts when adapting to new domains (i.e. environments, persons and locations) and poor performance for real-time recognition. In this paper, we propose DI-Gesture, a domain-independent and real-time mmWave gesture recognition system. Specifically, we first derive the signal variation corresponding to human gestures with spatial-temporal processing. To enhance the robustness of the system and reduce data collecting efforts, we design a data augmentation framework based on the correlation between signal patterns and gesture variations. Furthermore, we propose a dynamic window mechanism to perform gesture segmentation automatically and accurately, thus enable real-time recognition. Finally, we build a lightweight neural network to extract spatial-temporal information from the data for gesture classification. Extensive experimental results show DI-Gesture achieves an average accuracy of 97.92%, 99.18% and 98.76% for new users, environments and locations, respectively. In real-time scenario, the accuracy of DI-Gesutre reaches over 97% with average inference time of 2.87ms, which demonstrates the superior robustness and effectiveness of our system.

【4】 A Novel Approach for Deterioration and Damage Identification in Building Structures Based on Stockwell-Transform and Deep Convolutional Neural Network 标题：基于斯托克韦尔变换和深卷积神经网络的建筑结构劣化损伤识别新方法 链接：https://arxiv.org/abs/2111.06155

作者：Vahid Reza Gharehbaghi,Hashem Kalbkhani,Ehsan Noroozinejad Farsangi,T. Y. Yang,Andy Nguyene,Seyedali Mirjalili,C. Málaga-Chuquitaype 机构：a Research Scholar, Kharazmi University, Tehran, Iran, b AProfessor, Department of Electrical Engineering, Urmia University of Technology, Urmia, Iran, (h.kalbkhaniuut.ac.ir), c AProfessor, Graduate University of Advanced Technology 备注：11 figures and 11 Tables, Accepted in Journal of Structural Integrity and Maintenance 摘要：本文提出了一种新的退化和损伤识别方法（DIP），并将其应用于建筑模型。在这些类型的结构上应用相关的挑战与响应的强相关性有关，在处理具有高噪声水平的真实环境振动时，响应的强相关性变得更加复杂。因此，利用低成本环境振动设计DIP，以使用Stockwell变换（ST）生成频谱图来分析加速度响应。随后，ST输出成为两系列卷积神经网络（CNN）的输入，用于识别建筑物模型的劣化和损坏。据我们所知，这是第一次通过ST和CNN的高精度组合在建筑模型上评估损坏和劣化。 摘要：In this paper, a novel deterioration and damage identification procedure (DIP) is presented and applied to building models. The challenge associated with applications on these types of structures is related to the strong correlation of responses, which gets further complicated when coping with real ambient vibrations with high levels of noise. Thus, a DIP is designed utilizing low-cost ambient vibrations to analyze the acceleration responses using the Stockwell transform (ST) to generate spectrograms. Subsequently, the ST outputs become the input of two series of Convolutional Neural Networks (CNNs) established for identifying deterioration and damage to the building models. To the best of our knowledge, this is the first time that both damage and deterioration are evaluated on building models through a combination of ST and CNN with high accuracy.

【5】 Classification of the Chess Endgame problem using Logistic Regression, Decision Trees, and Neural Networks 标题：基于Logistic回归、决策树和神经网络的国际象棋终局问题分类 链接：https://arxiv.org/abs/2111.05976

作者：Mahmoud S. Fayed 机构：King Saud University, Riyadh, Saudi Arabia 摘要：在这项研究中，我们使用不同的算法，如逻辑回归、决策树和神经网络，对国际象棋终局问题进行分类。我们的实验表明，神经网络提供了最好的准确性（85%），然后是决策树（79%）。我们使用Microsoft Azure机器学习做了这些实验，作为在分类中使用可视化编程的案例研究。我们的实验表明，该工具功能强大，节省了大量时间，还可以使用更多的功能进行改进，以提高可用性并缩短学习曲线。我们还使用一种名为Ring的新编程语言开发了一个数据集可视化应用程序，我们的实验表明，这种语言具有类似Python的简单设计，同时集成了类似visualbasic的RAD工具，这有利于开源世界中的GUI开发 摘要：In this study we worked on the classification of the Chess Endgame problem using different algorithms like logistic regression, decision trees and neural networks. Our experiments indicates that the Neural Networks provides the best accuracy (85%) then the decision trees (79%). We did these experiments using Microsoft Azure Machine Learning as a case-study on using Visual Programming in classification. Our experiments demonstrates that this tool is powerful and save a lot of time, also it could be improved with more features that increase the usability and reduce the learning curve. We also developed an application for dataset visualization using a new programming language called Ring, our experiments demonstrates that this language have simple design like Python while integrates RAD tools like Visual Basic which is good for GUI development in the open-source world

【6】 Recognition of Patient Groups with Sleep Related Disorders using Bio-signal Processing and Deep Learning 标题：基于生物信号处理和深度学习的睡眠相关障碍患者群体识别 链接：https://arxiv.org/abs/2111.05917

作者：Delaram Jarchi,Javier Andreu-Perez,Mehrin Kiani,Oldrich Vysata,Jiri Kuchynka,Ales Prochazka,Saeid Sane 机构：Smart Health Technologies Group, School of Computer Science and Electronic Engineering; University of Essex, Embedded and Intelligent Systems Laboratory, School of Computer Science and Electronics, University of Essex, Colchester CO,SQ, UK 备注：None 摘要：准确诊断睡眠障碍对于临床评估和治疗至关重要。长期以来，多导睡眠图（PSG）一直用于检测各种睡眠障碍。在这项研究中，心电图（ECG）和肌电图（EMG）被用于识别呼吸和运动相关的睡眠障碍。生物信号处理通过利用熵和统计矩提取肌电特征来实现，此外，还开发了一种使用同步压缩小波变换（SSWT）的迭代脉冲峰值检测算法，用于从ECG可靠地提取心率和呼吸相关特征。设计了一个深度学习框架，以结合肌电图和心电图特征。该框架已被用于对四组患者进行分类：健康受试者、阻塞性睡眠呼吸暂停（OSA）患者、不宁腿综合征（RLS）患者以及OSA和RLS患者。建议的深度学习框架为我们制定的四类问题提供了72%的平均准确率和0.57的加权F1分数。 摘要：Accurately diagnosing sleep disorders is essential for clinical assessments and treatments. Polysomnography (PSG) has long been used for detection of various sleep disorders. In this research, electrocardiography (ECG) and electromayography (EMG) have been used for recognition of breathing and movement-related sleep disorders. Bio-signal processing has been performed by extracting EMG features exploiting entropy and statistical moments, in addition to developing an iterative pulse peak detection algorithm using synchrosqueezed wavelet transform (SSWT) for reliable extraction of heart rate and breathing-related features from ECG. A deep learning framework has been designed to incorporate EMG and ECG features. The framework has been used to classify four groups: healthy subjects, patients with obstructive sleep apnea (OSA), patients with restless leg syndrome (RLS) and patients with both OSA and RLS. The proposed deep learning framework produced a mean accuracy of 72% and weighted F1 score of 0.57 across subjects for our formulated four-class problem.

表征(1篇)

【1】 Discovering and Explaining the Representation Bottleneck of DNNs 标题：发现并解释DNNs的表示瓶颈 链接：https://arxiv.org/abs/2111.06236

作者：Huiqi Deng,Qihan Ren,Xu Chen,Hao Zhang,Jie Ren,Quanshi Zhang 机构：Shanghai Jiao Tong University 摘要：本文从深层神经网络（DNN）中编码的输入变量之间相互作用的复杂性出发，探讨了深度神经网络（DNN）特征表示的瓶颈。为此，我们关注输入变量之间的多阶交互，其中阶表示交互的复杂性。我们发现DNN更可能编码过于简单的交互和过于复杂的交互，但通常无法学习中等复杂度的交互。对于不同的任务，不同的DNN普遍存在这种现象。这一现象表明DNN和人类之间存在认知鸿沟，我们称之为表征瓶颈。我们从理论上证明了表征瓶颈的根本原因。此外，我们提出了一个损失来鼓励/惩罚特定复杂交互的学习，并分析了不同复杂交互的表征能力。 摘要：This paper explores the bottleneck of feature representations of deep neural networks (DNNs), from the perspective of the complexity of interactions between input variables encoded in DNNs. To this end, we focus on the multi-order interaction between input variables, where the order represents the complexity of interactions. We discover that a DNN is more likely to encode both too simple interactions and too complex interactions, but usually fails to learn interactions of intermediate complexity. Such a phenomenon is widely shared by different DNNs for different tasks. This phenomenon indicates a cognition gap between DNNs and human beings, and we call it a representation bottleneck. We theoretically prove the underlying reason for the representation bottleneck. Furthermore, we propose a loss to encourage/penalize the learning of interactions of specific complexities, and analyze the representation capacities of interactions of different complexities.

优化|敛散性(2篇)

【1】 Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games 标题：多人一般和博弈中相关均衡的近优无遗憾学习 链接：https://arxiv.org/abs/2111.06008

作者：Ioannis Anagnostides,Constantinos Daskalakis,Gabriele Farina,Maxwell Fishelson,Noah Golowich,Tuomas Sandholm 机构：† Carnegie Mellon University, Computer Science Department, ‡ MIT CSAIL, § Strategy Robot, Inc., ¶ Optimized Markets, Inc., # Strategic Machine, Inc. 摘要：最近，Daskalakis、Fishelson和Golowich（DFG）（NeurIPS`21）表明，如果多玩家一般和范式游戏中的所有代理都使用乐观乘法权重更新（OMWU），那么每个玩家在重复游戏$T$之后的外部遗憾是$O（\textrm{polylog}（T））$。我们将他们的结果从外部遗憾扩展到内部遗憾和交换遗憾，从而建立了以$\tilde{O}（T^{-1}）$的速率收敛到近似相关均衡的非耦合学习动力学。由于Chen和Peng（NeurIPS`20），这大大提高了先前的最佳相关平衡收敛速度$O（T^{-3/4}）$，并且在无遗憾框架内，它是最优的，最多可达$T$的多段对数因子。为了获得这些结果，我们开发了新技术，用于建立涉及不动点操作的学习动力学的高阶平滑度。具体地说，我们建立了Stoltz和Lugosi（Mach Learn`05）的无内部后悔学习动力学在组合空间上等价地由无外部后悔动力学模拟。这使得我们可以用多项式大小的马尔可夫链上的平稳分布计算来换取指数大小集上的线性变换（表现更好），从而使我们能够利用类似于DGF的技术来近似最优地限制内部遗憾。此外，我们为Blum和Mansour（BM）（JMLR`07）的经典算法建立了一个$O（\textrm{polylog}（T））$no-swap界。为此，我们引入了一种基于柯西积分公式的技术，该技术绕过了DFG更有限的组合参数。除了澄清BM的近似最优后悔保证外，我们的论点还深入了解了DFG技术在分析更复杂的学习算法时可以扩展和利用的各种方式。 摘要：Recently, Daskalakis, Fishelson, and Golowich (DFG) (NeurIPS`21) showed that if all agents in a multi-player general-sum normal-form game employ Optimistic Multiplicative Weights Update (OMWU), the external regret of every player is $O(\textrm{polylog}(T))$ after $T$ repetitions of the game. We extend their result from external regret to internal regret and swap regret, thereby establishing uncoupled learning dynamics that converge to an approximate correlated equilibrium at the rate of $\tilde{O}(T^{-1})$. This substantially improves over the prior best rate of convergence for correlated equilibria of $O(T^{-3/4})$ due to Chen and Peng (NeurIPS`20), and it is optimal -- within the no-regret framework -- up to polylogarithmic factors in $T$. To obtain these results, we develop new techniques for establishing higher-order smoothness for learning dynamics involving fixed point operations. Specifically, we establish that the no-internal-regret learning dynamics of Stoltz and Lugosi (Mach Learn`05) are equivalently simulated by no-external-regret dynamics on a combinatorial space. This allows us to trade the computation of the stationary distribution on a polynomial-sized Markov chain for a (much more well-behaved) linear transformation on an exponential-sized set, enabling us to leverage similar techniques as DGF to near-optimally bound the internal regret. Moreover, we establish an $O(\textrm{polylog}(T))$ no-swap-regret bound for the classic algorithm of Blum and Mansour (BM) (JMLR`07). We do so by introducing a technique based on the Cauchy Integral Formula that circumvents the more limited combinatorial arguments of DFG. In addition to shedding clarity on the near-optimal regret guarantees of BM, our arguments provide insights into the various ways in which the techniques by DFG can be extended and leveraged in the analysis of more involved learning algorithms.

【2】 Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum 标题：带动量的随机近似点算法的收敛性和稳定性 链接：https://arxiv.org/abs/2111.06171

作者：Junhyung Lyle Kim,Panos Toulis,Anastasios Kyrillidis 机构：Rice University, University of Chicago 摘要：动量随机梯度下降（SGDM）算法是许多优化场景中的主流算法，包括凸优化实例和非凸神经网络训练。然而，在随机环境中，动量会干扰梯度噪声，通常会导致特定的步长和动量选择，以保证收敛，而不考虑加速度。另一方面，近点法由于其数值稳定性和抗不完全调谐的弹性而备受关注。然而，他们的随机加速变量受到的关注有限：动量如何与（随机）近点方法的稳定性相互作用，在很大程度上尚未研究。为了解决这个问题，我们重点研究了带动量的随机近点算法（SPPAM）的收敛性和稳定性，并表明在适当的超参数调整下，SPPAM比带更好收缩因子的随机近点算法（SPPA）具有更快的线性收敛速度。在稳定性方面，我们表明SPPAM比SGDM更依赖于问题常数，允许更大范围的步长和动量，从而导致收敛。 摘要：Stochastic gradient descent with momentum (SGDM) is the dominant algorithm in many optimization scenarios, including convex optimization instances and non-convex neural network training. Yet, in the stochastic setting, momentum interferes with gradient noise, often leading to specific step size and momentum choices in order to guarantee convergence, set aside acceleration. Proximal point methods, on the other hand, have gained much attention due to their numerical stability and elasticity against imperfect tuning. Their stochastic accelerated variants though have received limited attention: how momentum interacts with the stability of (stochastic) proximal point methods remains largely unstudied. To address this, we focus on the convergence and stability of the stochastic proximal point algorithm with momentum (SPPAM), and show that SPPAM allows a faster linear convergence rate compared to stochastic proximal point algorithm (SPPA) with a better contraction factor, under proper hyperparameter tuning. In terms of stability, we show that SPPAM depends on problem constants more favorably than SGDM, allowing a wider range of step size and momentum that lead to convergence.

预测|估计(3篇)

【1】 Learning via Long Short-Term Memory (LSTM) network for predicting strains in Railway Bridge members under train induced vibration 标题：基于长短期记忆(LSTM)网络的铁路桥梁构件列车振动应变预测 链接：https://arxiv.org/abs/2111.06259

作者：Amartya Dutta,Kamaljyoti Nath 机构：Indian Institute of Information, Technology, Guwahati, India, Corresponding author, Indian Institute of Technology 备注：Accepted in ICDSMLA 2020 摘要：近年来，利用机器学习工具进行桥梁健康监测已成为一种高效、经济的方法。在本研究中，利用了IIT Guwahati之前进行的研究中得出的铁路桥梁构件应变。这些应变数据是在列车通过桥梁时从现有桥梁收集的。LSTM用于训练网络并预测铁路桥梁不同构件的应变。实际现场数据已用于使用单个构件的应变数据预测不同构件中的应变，但已观察到它们与地面真值非常一致。尽管数据中存在大量噪声，但这表明了LSTM在训练和预测方面的有效性，即使是在有噪声的现场数据中。这可以很容易地利用较少的传感器从桥梁收集数据，并通过LSTM网络预测其他构件的应变数据。 摘要：Bridge health monitoring using machine learning tools has become an efficient and cost-effective approach in recent times. In the present study, strains in railway bridge member, available from a previous study conducted by IIT Guwahati has been utilized. These strain data were collected from an existing bridge while trains were passing over the bridge. LSTM is used to train the network and to predict strains in different members of the railway bridge. Actual field data has been used for the purpose of predicting strain in different members using strain data from a single member, yet it has been observed that they are quite agreeable to those of ground truth values. This is in spite of the fact that a lot of noise existed in the data, thus showing the efficacy of LSTM in training and predicting even from noisy field data. This may easily open up the possibility of collecting data from the bridge with a much lesser number of sensors and predicting the strain data in other members through LSTM network.

【2】 Improvements to short-term weather prediction with recurrent-convolutional networks 标题：利用递归-卷积网络改进短期天气预报 链接：https://arxiv.org/abs/2111.06240

作者：Jussi Leinonen 机构：Federal Office of Meteorology and Climatology MeteoSwiss, Locarno-Monti, Switzerland 备注：6 pages, 4 figures. Submitted to The Special Session on the Weather4cast Competition at IEEE Big Data Conference 2021 摘要：Weather4cast 2021竞赛为参与者提供了一项任务，即预测卫星气象数据二维场的时间演变。本文描述了作者在第一阶段比赛取得初步成功后，在第二阶段进一步改进模型的努力。改进包括较浅的模型变体，与较深的版本相比具有竞争力，采用AdaFaith优化器，改进对其中一个预测变量的处理，发现训练集不能很好地代表验证集，以及整合多个模型以进一步改进结果。竞赛指标的最大量化改进可归因于竞赛第二阶段可用训练数据的增加，其次是模型集成的影响。定性结果表明，该模型可以预测场的时间演化，包括场随时间的运动，从对近期的精确预测开始，并在以后的帧中模糊输出，以解释增加的不确定性。 摘要：The Weather4cast 2021 competition gave the participants a task of predicting the time evolution of two-dimensional fields of satellite-based meteorological data. This paper describes the author's efforts, after initial success in the first stage of the competition, to improve the model further in the second stage. The improvements consisted of a shallower model variant that is competitive against the deeper version, adoption of the AdaBelief optimizer, improved handling of one of the predicted variables where the training set was found not to represent the validation set well, and ensembling multiple models to improve the results further. The largest quantitative improvements to the competition metrics can be attributed to the increased amount of training data available in the second stage of the competition, followed by the effects of model ensembling. Qualitative results show that the model can predict the time evolution of the fields, including the motion of the fields over time, starting with sharp predictions for the immediate future and blurring of the outputs in later frames to account for the increased uncertainty.

【3】 Benefit-aware Early Prediction of Health Outcomes on Multivariate EEG Time Series 标题：基于多变量脑电时间序列的效益意识健康结局早期预测 链接：https://arxiv.org/abs/2111.06032

作者：Shubhranshu Shekhar,Dhivya Eswaran,Bryan Hooi,Jonathan Elmer,Christos Faloutsos,Leman Akoglu 机构：Heinz College & Machine Learning, Dept., Carnegie Mellon University, Department of Computer Science, School of Computing, National University of Singapore, Departments of Emergency Medicine, Critical Care Medicine and Neurology, University of Pittsburgh 备注：arxiv submission 摘要：鉴于一名心脏骤停患者在ICU（重症监护病房）接受大脑活动监测，我们如何尽早预测他们的健康结果？早期决策在许多应用中至关重要，例如，监测患者可能有助于早期干预和改善护理。另一方面，脑电图数据的早期预测带来了几个挑战：（i）早期-准确度权衡；观察更多数据通常会提高准确性，但会牺牲早期性，（ii）大规模（用于训练）和流式（在线决策）数据处理，以及（iii）多变量（由于多个电极）和多长度（由于患者住院时间不同）时间序列。受这个现实世界应用程序的推动，我们介绍了BeneFitter，它将早期预测带来的成本节约以及错误分类带来的成本注入一个统一的特定领域目标，称为benefit。统一这两个数量可以让我们直接估计单个目标（即效益），重要的是，它准确地指示何时输出预测：效益估计何时变为正值。BeneFitter（a）效率高、速度快，训练时间与输入序列数呈线性关系，可实时操作以进行决策，（b）可处理多变量和可变长度的时间序列，适用于患者数据，以及（c）效率高，与竞争对手相比，可节省2倍的时间，精确度相同或更好。 摘要：Given a cardiac-arrest patient being monitored in the ICU (intensive care unit) for brain activity, how can we predict their health outcomes as early as possible? Early decision-making is critical in many applications, e.g. monitoring patients may assist in early intervention and improved care. On the other hand, early prediction on EEG data poses several challenges: (i) earliness-accuracy trade-off; observing more data often increases accuracy but sacrifices earliness, (ii) large-scale (for training) and streaming (online decision-making) data processing, and (iii) multi-variate (due to multiple electrodes) and multi-length (due to varying length of stay of patients) time series. Motivated by this real-world application, we present BeneFitter that infuses the incurred savings from an early prediction as well as the cost from misclassification into a unified domain-specific target called benefit. Unifying these two quantities allows us to directly estimate a single target (i.e. benefit), and importantly, dictates exactly when to output a prediction: when benefit estimate becomes positive. BeneFitter (a) is efficient and fast, with training time linear in the number of input sequences, and can operate in real-time for decision-making, (b) can handle multi-variate and variable-length time-series, suitable for patient data, and (c) is effective, providing up to 2x time-savings with equal or better accuracy as compared to competitors.

其他神经网络|深度学习|模型|建模(18篇)

【1】 Full-Body Visual Self-Modeling of Robot Morphologies 标题：机器人形态的全身视觉自建模 链接：https://arxiv.org/abs/2111.06389

作者：Boyuan Chen,Robert Kwiatkowski,Carl Vondrick,Hod Lipson 机构：Columbia University 备注：Project website: this https URL 摘要：物理身体的内部计算模型是机器人和动物计划和控制其行动的能力的基础。这些“自我模型”允许机器人考虑多个可能的未来行动的结果，而不在物理现实中尝试它们。完全数据驱动自建模的最新进展使机器能够直接从任务无关的交互数据中学习自己的正向运动学。然而，正向运动学模型只能预测形态的有限方面，如末端执行器的位置或关节和质量的速度。一个关键的挑战是建模整个形态学和运动学，而不事先知道形态学的哪些方面与未来任务相关。在这里，我们提出了一种更有用的自建模形式，可以根据机器人的状态回答空间占用查询，而不是直接建模正向运动学。这种查询驱动的自模型在空间域中是连续的、高效的、完全可微的和运动感知的。在物理实验中，我们演示了视觉自我模型如何精确到工作空间的1%，从而使机器人能够执行各种运动规划和控制任务。视觉自建模还可以让机器人检测、定位和恢复现实世界中的损坏，从而提高机器的弹性。我们的项目网站位于：https://robot-morphology.cs.columbia.edu/ 摘要：Internal computational models of physical bodies are fundamental to the ability of robots and animals alike to plan and control their actions. These "self-models" allow robots to consider outcomes of multiple possible future actions, without trying them out in physical reality. Recent progress in fully data-driven self-modeling has enabled machines to learn their own forward kinematics directly from task-agnostic interaction data. However, forward-kinema\-tics models can only predict limited aspects of the morphology, such as the position of end effectors or velocity of joints and masses. A key challenge is to model the entire morphology and kinematics, without prior knowledge of what aspects of the morphology will be relevant to future tasks. Here, we propose that instead of directly modeling forward-kinematics, a more useful form of self-modeling is one that could answer space occupancy queries, conditioned on the robot's state. Such query-driven self models are continuous in the spatial domain, memory efficient, fully differentiable and kinematic aware. In physical experiments, we demonstrate how a visual self-model is accurate to about one percent of the workspace, enabling the robot to perform various motion planning and control tasks. Visual self-modeling can also allow the robot to detect, localize and recover from real-world damage, leading to improved machine resiliency. Our project website is at: https://robot-morphology.cs.columbia.edu/

【2】 Learning Signal-Agnostic Manifolds of Neural Fields 标题：学习信号不可知的神经场流形 链接：https://arxiv.org/abs/2111.06387

作者：Yilun Du,Katherine M. Collins,Joshua B. Tenenbaum,Vincent Sitzmann 机构：Katherine Collins, MIT CSAIL, MIT BCS, MIT CBMM 备注：NeurIPS 2021, additional results and code at this https URL 摘要：深度神经网络已被广泛用于跨图像、形状和音频信号等模式学习数据集的潜在结构。然而，现有的模型通常依赖于模态，需要定制的体系结构和目标来处理不同类别的信号。我们利用神经场以模态独立的方式捕获图像、形状、音频和跨模态视听域中的底层结构。我们的任务是学习流形，我们的目标是推断数据所在的低维局部线性子空间。通过加强流形、局部线性和局部等距的覆盖，我们的模型（称为GEM）学习捕获跨模式数据集的底层结构。然后，我们可以沿着流形的线性区域移动，以获得样本之间的感知一致性插值，并可以进一步使用GEM恢复流形上的点，不仅收集输入图像的各种完整信息，还收集音频或图像信号的跨模态幻觉。最后，我们展示了通过遍历GEM的底层流形，我们可以在信号域中生成新样本。有关代码和其他结果，请访问https://yilundu.github.io/gem/. 摘要：Deep neural networks have been used widely to learn the latent structure of datasets, across modalities such as images, shapes, and audio signals. However, existing models are generally modality-dependent, requiring custom architectures and objectives to process different classes of signals. We leverage neural fields to capture the underlying structure in image, shape, audio and cross-modal audiovisual domains in a modality-independent manner. We cast our task as one of learning a manifold, where we aim to infer a low-dimensional, locally linear subspace in which our data resides. By enforcing coverage of the manifold, local linearity, and local isometry, our model -- dubbed GEM -- learns to capture the underlying structure of datasets across modalities. We can then travel along linear regions of our manifold to obtain perceptually consistent interpolations between samples, and can further use GEM to recover points on our manifold and glean not only diverse completions of input images, but cross-modal hallucinations of audio or image signals. Finally, we show that by walking across the underlying manifold of GEM, we may generate new samples in our signal domains. Code and additional results are available at https://yilundu.github.io/gem/.

【3】 Learning from Mistakes -- A Framework for Neural Architecture Search 标题：从错误中学习--一个神经结构搜索框架 链接：https://arxiv.org/abs/2111.06353

作者：Bhanu Garg,Li Zhang,Pradyumna Sridhara,Ramtin Hosseini,Eric Xing,Pengtao Xie 机构： University of California, San Diego, USA, Zhejiang University, China, Carnegie Mellon University, USA 摘要：从错误中学习是一种有效的人类学习技巧，学习者更多地关注错误发生的主题，从而加深他们的理解。在本文中，我们研究了这种人类学习策略是否可以应用于机器学习。我们提出了一种新的机器学习方法，称为从错误中学习（LFM），学习者通过在复习过程中更多地关注错误来提高学习能力。我们将LFM描述为一个三阶段优化问题：1）学习者学习；2） 学习者专注于错误，重新学习；3） 学习者验证其学习。我们开发了一种有效的算法来解决线性调频问题。我们将LFM框架应用于CIFAR-10、CIFAR-100和Imagenet上的神经结构搜索。实验结果有力地证明了我们模型的有效性。 摘要：Learning from one's mistakes is an effective human learning technique where the learners focus more on the topics where mistakes were made, so as to deepen their understanding. In this paper, we investigate if this human learning strategy can be applied in machine learning. We propose a novel machine learning method called Learning From Mistakes (LFM), wherein the learner improves its ability to learn by focusing more on the mistakes during revision. We formulate LFM as a three-stage optimization problem: 1) learner learns; 2) learner re-learns focusing on the mistakes, and; 3) learner validates its learning. We develop an efficient algorithm to solve the LFM problem. We apply the LFM framework to neural architecture search on CIFAR-10, CIFAR-100, and Imagenet. Experimental results strongly demonstrate the effectiveness of our model.

【4】 Raman spectroscopy in open world learning settings using the Objectosphere approach 标题：使用对象圈方法的开放世界学习环境中的拉曼光谱 链接：https://arxiv.org/abs/2111.06268

作者：Yaroslav Balytskyi,Justin Bendesky,Tristan Paul,Guy Hagen,Kelly McNear 机构：Department of Physics and Energy Science, Colorado Springs, CO, USA, UCCS BioFrontiers Center, University of Colorado Colorado Springs, Department of Chemistry, New York University, New York, NY , USA, ), arXiv:,.,v, [cs.LG] , Nov 摘要：拉曼光谱与机器学习相结合，作为一种快速、灵敏、无标记的识别方法，在临床应用中具有重要的前景。这些方法可以很好地对包含在训练阶段发生的类的数据进行分类。然而，在实践中，总有一些物质的光谱尚未采集或未知，当输入数据远离训练集且包含训练阶段未看到的新类别时，会记录大量误报，从而限制了这些算法的临床相关性。在这里，我们展示了通过实现最近引入的熵开集和对象层损失函数可以克服这些障碍。为了证明这种方法的有效性，我们编译了一个40个化学类别的拉曼光谱数据库，将它们分为20个由氨基酸组成的生物相关类别，10个由生物相关化学品组成的不相关类别，以及神经网络以前从未见过的10个类别，由多种其他化学物质组成。我们证明，这种方法使网络能够有效地识别未知类，同时保持已知类的高精度，在保持已知类的高精度的同时显著减少误报的数量，这将使这项技术能够弥合实验室实验和临床应用之间的差距。 摘要：Raman spectroscopy in combination with machine learning has significant promise for applications in clinical settings as a rapid, sensitive, and label-free identification method. These approaches perform well in classifying data that contains classes that occur during the training phase. However, in practice, there are always substances whose spectra have not yet been taken or are not yet known and when the input data are far from the training set and include new classes that were not seen at the training stage, a significant number of false positives are recorded which limits the clinical relevance of these algorithms. Here we show that these obstacles can be overcome by implementing recently introduced Entropic Open Set and Objectosphere loss functions. To demonstrate the efficiency of this approach, we compiled a database of Raman spectra of 40 chemical classes separating them into 20 biologically relevant classes comprised of amino acids, 10 irrelevant classes comprised of bio-related chemicals, and 10 classes that the Neural Network has not seen before, comprised of a variety of other chemicals. We show that this approach enables the network to effectively identify the unknown classes while preserving high accuracy on the known ones, dramatically reducing the number of false positives while preserving high accuracy on the known classes, which will allow this technique to bridge the gap between laboratory experiments and clinical applications.

【5】 Data-Centric Engineering: integrating simulation, machine learning and statistics. Challenges and Opportunities 标题：以数据为中心的工程：集成仿真、机器学习和统计。挑战与机遇 链接：https://arxiv.org/abs/2111.06223

作者：Indranil Pan,Lachlan Mason,Omar Matar 机构：Imperial College London, UK, SW,AZ, The Alan Turing Institute, UK, NW,DB 备注：20 pages, 2 figures 摘要：机器学习的最新进展，加上低成本计算、廉价流式传感器、数据存储和云技术的可用性，导致了广泛的多学科研究活动，商业利益相关者对此产生了极大的兴趣和投资。基于物理方程的机械模型和纯数据驱动的统计方法代表了建模谱的两端。新的以数据为中心的混合工程方法，充分利用了这两个领域的优点，并将仿真和数据集成在一起，正在成为一种强大的工具，对物理学科产生变革性影响。我们回顾了集成仿真、机器学习和统计的新兴领域中的关键研究趋势和应用场景。我们强调了这样一个综合愿景所带来的机遇，并概述了阻碍其实现的关键挑战。我们还讨论了该领域翻译方面的瓶颈以及现有劳动力和未来大学毕业生的长期技能提升需求。 摘要：Recent advances in machine learning, coupled with low-cost computation, availability of cheap streaming sensors, data storage and cloud technologies, has led to widespread multi-disciplinary research activity with significant interest and investment from commercial stakeholders. Mechanistic models, based on physical equations, and purely data-driven statistical approaches represent two ends of the modelling spectrum. New hybrid, data-centric engineering approaches, leveraging the best of both worlds and integrating both simulations and data, are emerging as a powerful tool with a transformative impact on the physical disciplines. We review the key research trends and application scenarios in the emerging field of integrating simulations, machine learning, and statistics. We highlight the opportunities that such an integrated vision can unlock and outline the key challenges holding back its realisation. We also discuss the bottlenecks in the translational aspects of the field and the long-term upskilling requirements of the existing workforce and future university graduates.

【6】 Training neural networks with synthetic electrocardiograms 标题：用合成心电图训练神经网络 链接：https://arxiv.org/abs/2111.06175

作者：Matti Kaisti,Juho Laitala,Antti Airola 机构： Department of Computing, Digital Health Lab, University of Turku, Turku , Finland 摘要：我们提出了一种用模拟可穿戴单导联心电图监护仪产生信号的合成心电图训练神经网络的方法。我们使用域随机化，其中合成信号特性（如波形、RR间隔和噪声）对于每个训练示例都是不同的。将使用合成数据训练的模型与使用真实数据训练的模型进行比较。在不同体力活动期间记录的心电图和心房颤动中检测r波用于比较模型。通过允许随机化增加超出通常在真实世界数据中观察到的性能，性能等同于或取代了用真实数据训练的网络的性能。实验表明，在不同的测试集上使用不同的种子和训练示例，不需要任何特定于测试集的调优，就可以获得鲁棒性能。该方法可以训练神经网络，使用几乎免费的方法收集具有准确标签的数据，而无需手动注释，并且当在心电图生成中使用特定于疾病的先验信息时，它为扩展合成数据在心脏病分类中的使用开辟了可能性。此外，可以控制数据的分布，消除通常在健康相关数据中观察到的阶级不平衡，此外，生成的数据本身是私有的。 摘要：We present a method for training neural networks with synthetic electrocardiograms that mimic signals produced by a wearable single lead electrocardiogram monitor. We use domain randomization where the synthetic signal properties such as the waveform shape, RR-intervals and noise are varied for every training example. Models trained with synthetic data are compared to their counterparts trained with real data. Detection of r-waves in electrocardiograms recorded during different physical activities and in atrial fibrillation is used to compare the models. By allowing the randomization to increase beyond what is typically observed in the real-world data the performance is on par or superseding the performance of networks trained with real data. Experiments show robust performance with different seeds and training examples on different test sets without any test set specific tuning. The method makes possible to train neural networks using practically free-to-collect data with accurate labels without the need for manual annotations and it opens up the possibility of extending the use of synthetic data on cardiac disease classification when disease specific a priori information is used in the electrocardiogram generation. Additionally the distribution of data can be controlled eliminating class imbalances that are typically observed in health related data and additionally the generated data is inherently private.

【7】 Characterization of Frequent Online Shoppers using Statistical Learning with Sparsity 标题：基于稀疏性统计学习的频繁在线购物者特征研究 链接：https://arxiv.org/abs/2111.06057

作者：Rajiv Sambasivan,Mark Burgess,Jörg Schad,Arthur Keen,Christopher Woodward,Alexander Geenen,Sachin Sharma 机构：ArangoDB Inc, San Mateo, CA, Chitek-i 摘要：开发让客户满意的购物体验需要企业了解客户的品味。这项工作报告了一种方法，通过将零售分析和统计学习的思想与稀疏性相结合，来了解在线礼品店常客的购物偏好。购物活动表示为二部图。该图通过应用基于稀疏性的统计学习方法进行细化。这些方法是可解释的，揭示了关于客户偏好以及推动商店收入的产品的见解。 摘要：Developing shopping experiences that delight the customer requires businesses to understand customer taste. This work reports a method to learn the shopping preferences of frequent shoppers to an online gift store by combining ideas from retail analytics and statistical learning with sparsity. Shopping activity is represented as a bipartite graph. This graph is refined by applying sparsity-based statistical learning methods. These methods are interpretable and reveal insights about customers' preferences as well as products driving revenue to the store.

【8】 Climate Modeling with Neural Diffusion Equations 标题：基于神经扩散方程的气候模拟 链接：https://arxiv.org/abs/2111.06011

作者：Jeehyun Hwang,Jeongwhan Choi,Hwangyong Choi,Kookjin Lee,Dongeun Lee,Noseong Park 机构：Yonsei University, Seoul, South Korea, Arizona State University, Tempe, AZ, USA, Texas A&M University–Commerce, Commerce, TX, USA 备注：Accepted by ICDM 2021 摘要：由于深度学习技术的显著发展，人们已经做出了一系列努力来构建基于深度学习的气候模型。鉴于大多数模型采用递归神经网络和/或图形神经网络，我们基于神经常微分方程（NODE）和扩散方程这两个概念设计了一个新的气候模型。许多涉及粒子布朗运动的物理过程可以用扩散方程来描述，因此，它被广泛用于气候模拟。另一方面，神经常微分方程（节点）从数据中学习ODE的潜在控制方程。在我们提出的方法中，我们将它们结合到一个单一的框架中，并提出了一个称为神经扩散方程（NDE）的概念。我们的NDE配备了扩散方程和一个额外的神经网络来模拟固有的不确定性，可以学习一个适当的潜在控制方程，最好地描述给定的气候数据集。在我们对两个真实数据集和一个合成数据集以及11个基线进行的实验中，我们的方法始终比现有的基线具有更大的优势。 摘要：Owing to the remarkable development of deep learning technology, there have been a series of efforts to build deep learning-based climate models. Whereas most of them utilize recurrent neural networks and/or graph neural networks, we design a novel climate model based on the two concepts, the neural ordinary differential equation (NODE) and the diffusion equation. Many physical processes involving a Brownian motion of particles can be described by the diffusion equation and as a result, it is widely used for modeling climate. On the other hand, neural ordinary differential equations (NODEs) are to learn a latent governing equation of ODE from data. In our presented method, we combine them into a single framework and propose a concept, called neural diffusion equation (NDE). Our NDE, equipped with the diffusion equation and one more additional neural network to model inherent uncertainty, can learn an appropriate latent governing equation that best describes a given climate dataset. In our experiments with two real-world and one synthetic datasets and eleven baselines, our method consistently outperforms existing baselines by non-trivial margins.

【9】 Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training 标题：Amazon SageMaker模型并行性：一个通用而灵活的大型模型训练框架 链接：https://arxiv.org/abs/2111.05972

作者：Can Karakus,Rahul Huilgol,Fei Wu,Anirudh Subramanian,Cade Daniel,Derya Cavdar,Teng Xu,Haohan Chen,Arash Rahnama,Luis Quintela 备注：24 pages. Submitted for review 摘要：随着深度学习模型规模的快速增长，需要用于大型模型训练的系统级解决方案。我们介绍了Amazon SageMaker model parallelism，这是一个与Pyrotch集成的软件库，可以使用model parallelism和其他节省内存的功能轻松训练大型模型。与现有解决方案相比，SageMaker库的实现更具通用性和灵活性，因为它可以在任意模型体系结构上自动划分和运行管道并行，而代码更改最少，并且还为tensor并行提供了通用和可扩展的框架，它支持更广泛的用例，模块化程度足以轻松应用于新的训练脚本。该库还在更大程度上保留了原生PyTorch用户体验，支持模块重用和动态图形，同时让用户完全控制训练步骤的细节。我们评估了GPT-3、RoBERTa、BERT和神经协同过滤的性能，并展示了与现有解决方案相比的竞争力。 摘要：With deep learning models rapidly growing in size, systems-level solutions for large-model training are required. We present Amazon SageMaker model parallelism, a software library that integrates with PyTorch, and enables easy training of large models using model parallelism and other memory-saving features. In contrast to existing solutions, the implementation of the SageMaker library is much more generic and flexible, in that it can automatically partition and run pipeline parallelism over arbitrary model architectures with minimal code change, and also offers a general and extensible framework for tensor parallelism, which supports a wider range of use cases, and is modular enough to be easily applied to new training scripts. The library also preserves the native PyTorch user experience to a much larger degree, supporting module re-use and dynamic graphs, while giving the user full control over the details of the training step. We evaluate performance over GPT-3, RoBERTa, BERT, and neural collaborative filtering, and demonstrate competitive performance over existing solutions.

【10】 Linear Speedup in Personalized Collaborative Learning 标题：个性化协作学习中的线性加速比 链接：https://arxiv.org/abs/2111.05968

作者：El Mahdi Chayti,Sai Praneeth Karimireddy,Sebastian U. Stich,Nicolas Flammarion,Martin Jaggi 机构：EPFL 摘要：联邦学习中的个性化可以通过权衡模型的偏差（通过使用可能不同的其他用户的数据引入）和方差（由于任何单个用户的数据量有限），提高模型对用户的准确性。为了开发最佳平衡这种平衡的训练算法，有必要扩展我们的理论基础。在这项工作中，我们将个性化协作学习问题形式化为用户目标$f_0（x）$的随机优化，同时允许访问其他用户的$N$相关但不同的目标$\{f_1（x），\dots，f_N（x）\}$。在这种情况下，我们给出了两种算法的收敛性保证——一种流行的个性化方法，称为\emph{加权梯度平均}，以及一种新的\emph{偏差校正}方法——并探索在何种条件下，我们可以最佳地权衡他们的偏差，以减少方差，并实现线性加速w.r.t.\N用户数$N$。此外，我们还实证研究了他们的表现，证实了我们的理论见解。 摘要：Personalization in federated learning can improve the accuracy of a model for a user by trading off the model's bias (introduced by using data from other users who are potentially different) against its variance (due to the limited amount of data on any single user). In order to develop training algorithms that optimally balance this trade-off, it is necessary to extend our theoretical foundations. In this work, we formalize the personalized collaborative learning problem as stochastic optimization of a user's objective $f_0(x)$ while given access to $N$ related but different objectives of other users $\{f_1(x), \dots, f_N(x)\}$. We give convergence guarantees for two algorithms in this setting -- a popular personalization method known as \emph{weighted gradient averaging}, and a novel \emph{bias correction} method -- and explore conditions under which we can optimally trade-off their bias for a reduction in variance and achieve linear speedup w.r.t.\ the number of users $N$. Further, we also empirically study their performance confirming our theoretical insights.

【11】 Robust Learning via Ensemble Density Propagation in Deep Neural Networks 标题：基于集成密度传播的深度神经网络鲁棒学习 链接：https://arxiv.org/abs/2111.05953

作者：Giuseppina Carannante,Dimah Dera,Ghulam Rasool,Nidhal C. Bouaynaya,Lyudmila Mihaylova 机构：⋆ Rowan University, Department of Electrical and Computer Engineering, Glassboro, NJ, † University of Sheffield, Department of Automatic Control and Systems Engineering, United Kingdom 备注：submitted to 2020 IEEE International Workshop on Machine Learning for Signal Processing 摘要：对于深度神经网络（DNN），在不确定、嘈杂或敌对环境中学习是一项具有挑战性的任务。我们提出了一种新的基于贝叶斯估计和变分推理的鲁棒学习方法。我们提出了密度通过DNN层传播的问题，并使用系综密度传播（EnDP）方案进行了求解。EnDP方法允许我们将变分概率分布的矩传播到贝叶斯DNN的各个层，从而能够估计模型输出处预测分布的平均值和协方差。我们使用MNIST和CIFAR-10数据集进行的实验表明，经过训练的模型对随机噪声和敌对攻击的鲁棒性有显著提高。 摘要：Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for robust learning that builds upon Bayesian estimation and Variational Inference. We formulate the problem of density propagation through layers of a DNN and solve it using an Ensemble Density Propagation (EnDP) scheme. The EnDP approach allows us to propagate moments of the variational probability distribution across the layers of a Bayesian DNN, enabling the estimation of the mean and covariance of the predictive distribution at the output of the model. Our experiments using MNIST and CIFAR-10 datasets show a significant improvement in the robustness of the trained models to random noise and adversarial attacks.

【12】 Self-Compression in Bayesian Neural Networks 标题：贝叶斯神经网络中的自压缩 链接：https://arxiv.org/abs/2111.05950

作者：Giuseppina Carannante,Dimah Dera,Ghulam Rasool,Nidhal C. Bouaynaya 机构：Rowan University, Department of Electrical and Computer Engineering, Glassboro, NJ 备注：submitted to 2020 IEEE International Workshop on Machine Learning for Signal Processing 摘要：机器学习模型已经在各种任务上实现了人类水平的性能。这一成功的代价是高昂的计算和存储开销，这使得机器学习算法难以部署在边缘设备上。通常，为了提高性能，必须部分牺牲准确性，以减少内存使用和能耗。现有方法通过降低参数精度或消除冗余参数来压缩网络。在本文中，我们通过贝叶斯框架对网络压缩提出了新的见解。我们表明，贝叶斯神经网络自动发现模型参数中的冗余，从而实现自压缩，这与不确定性通过网络层的传播有关。我们的实验结果表明，通过删除网络本身识别的参数，可以成功地压缩网络结构，同时保持相同的精度水平。 摘要：Machine learning models have achieved human-level performance on various tasks. This success comes at a high cost of computation and storage overhead, which makes machine learning algorithms difficult to deploy on edge devices. Typically, one has to partially sacrifice accuracy in favor of an increased performance quantified in terms of reduced memory usage and energy consumption. Current methods compress the networks by reducing the precision of the parameters or by eliminating redundant ones. In this paper, we propose a new insight into network compression through the Bayesian framework. We show that Bayesian neural networks automatically discover redundancy in model parameters, thus enabling self-compression, which is linked to the propagation of uncertainty through the layers of the network. Our experimental results show that the network architecture can be successfully compressed by deleting parameters identified by the network itself while retaining the same level of accuracy.

【13】 How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning 标题：如何利用可解释机器学习发现超材料中的隐藏模式 链接：https://arxiv.org/abs/2111.05949

作者：Zhi Chen,Alexander Ogren,Chiara Daraio,L. Catherine Brinson,Cynthia Rudin 机构：Duke University, California Institute of Technology 备注：Under review 摘要：超材料是具有工程几何微观和细观结构的复合材料，可导致不寻常的物理特性，如负泊松比或超低剪切阻力。周期性超材料由重复的单胞组成，这些单胞内的几何图案影响弹性波或声波的传播并控制色散。在这项工作中，我们开发了一个新的可解释的、多分辨率的机器学习框架，用于在材料的单位细胞中发现揭示其动态特性的模式。具体来说，我们提出了两种新的可解释的超材料表示法，称为形状频率特征和单位细胞模板。使用这些特征类建立的机器学习模型可以准确地预测动态材料特性。这些特征表示（尤其是单位单元模板）具有一个有用的特性：它们可以对更高分辨率的设计进行操作。通过学习可通过形状频率特征或单元模板可靠转移到更精细分辨率设计空间的关键粗尺度图案，我们几乎可以自由设计单元的精细分辨率特征，而无需改变粗尺度物理。通过这种多分辨率方法，我们能够设计具有允许或不允许波传播的目标频率范围（频率带隙）的材料。我们的方法产生了主要的好处：（1）与材料科学的典型机器学习方法不同，我们的模型是可解释的，（2）我们的方法利用多分辨率特性，（3）我们的方法提供了设计灵活性。 摘要：Metamaterials are composite materials with engineered geometrical micro- and meso-structures that can lead to uncommon physical properties, like negative Poisson's ratio or ultra-low shear resistance. Periodic metamaterials are composed of repeating unit-cells, and geometrical patterns within these unit-cells influence the propagation of elastic or acoustic waves and control dispersion. In this work, we develop a new interpretable, multi-resolution machine learning framework for finding patterns in the unit-cells of materials that reveal their dynamic properties. Specifically, we propose two new interpretable representations of metamaterials, called shape-frequency features and unit-cell templates. Machine learning models built using these feature classes can accurately predict dynamic material properties. These feature representations (particularly the unit-cell templates) have a useful property: they can operate on designs of higher resolutions. By learning key coarse scale patterns that can be reliably transferred to finer resolution design space via the shape-frequency features or unit-cell templates, we can almost freely design the fine resolution features of the unit-cell without changing coarse scale physics. Through this multi-resolution approach, we are able to design materials that possess target frequency ranges in which waves are allowed or disallowed to propagate (frequency bandgaps). Our approach yields major benefits: (1) unlike typical machine learning approaches to materials science, our models are interpretable, (2) our approaches leverage multi-resolution properties, and (3) our approach provides design flexibility.

【14】 Persia: A Hybrid System Scaling Deep Learning Based Recommenders up to 100 Trillion Parameters 标题：PERSIA：一种混合系统，可将基于深度学习的推荐器扩展到100万亿个参数 链接：https://arxiv.org/abs/2111.05897

作者：Xiangru Lian,Binhang Yuan,Xuefeng Zhu,Yulong Wang,Yongjun He,Honghuan Wu,Lei Sun,Haodong Lyu,Chengjun Liu,Xing Dong,Yiqiao Liao,Mingnan Luo,Congfei Zhang,Jingru Xie,Haonan Li,Lei Chen,Renjie Huang,Jianying Lin,Chengchun Shu,Xuezhong Qiu,Zhishan Liu,Dongying Kong,Lei Yuan,Hai Yu,Sen Yang,Ce Zhang,Ji Liu 机构：Kwai Inc., USA; ,Kuaishou Technology, China; ,ETH Zürich, Switzerland; 摘要：基于深度学习的模型主导了当前的产品推荐系统。此外，近年来，模型规模呈指数级增长——从2016年10亿参数的谷歌模型到最新的12万亿参数的Facebook模型。模型容量的每一次飞跃都带来了显著的质量提升，这让我们相信100万亿参数的时代即将到来。然而，即使在工业规模的数据中心内，此类模型的训练也是一项挑战。这一困难源于训练计算的惊人异构性——模型的嵌入层可能包含超过99.99%的模型总大小，这是非常内存密集的；而其余的神经网络计算量越来越大。为了支持如此庞大模型的训练，迫切需要一个高效的分布式训练系统。在本文中，我们通过仔细地共同设计优化算法和分布式系统架构来解决这一挑战。具体来说，为了保证训练效率和训练精度，我们设计了一种新的混合训练算法，其中嵌入层和稠密神经网络由不同的同步机制处理；然后我们构建了一个名为Persia（混合加速并行推荐训练系统）的系统来支持这种混合训练算法。通过理论论证和高达100万亿个参数的实证研究，证明了Persia系统设计和实施的合理性。我们公开提供波斯（在https://github.com/PersiaML/Persia)因此，任何人都可以轻松地训练一个100万亿参数规模的推荐模型。 摘要：Deep learning based models have dominated the current landscape of production recommender systems. Furthermore, recent years have witnessed an exponential growth of the model scale--from Google's 2016 model with 1 billion parameters to the latest Facebook's model with 12 trillion parameters. Significant quality boost has come with each jump of the model capacity, which makes us believe the era of 100 trillion parameters is around the corner. However, the training of such models is challenging even within industrial scale data centers. This difficulty is inherited from the staggering heterogeneity of the training computation--the model's embedding layer could include more than 99.99% of the total model size, which is extremely memory-intensive; while the rest neural network is increasingly computation-intensive. To support the training of such huge models, an efficient distributed training system is in urgent need. In this paper, we resolve this challenge by careful co-design of both the optimization algorithm and the distributed system architecture. Specifically, in order to ensure both the training efficiency and the training accuracy, we design a novel hybrid training algorithm, where the embedding layer and the dense neural network are handled by different synchronization mechanisms; then we build a system called Persia (short for parallel recommendation training system with hybrid acceleration) to support this hybrid training algorithm. Both theoretical demonstration and empirical study up to 100 trillion parameters have conducted to justified the system design and implementation of Persia. We make Persia publicly available (at https://github.com/PersiaML/Persia) so that anyone would be able to easily train a recommender model at the scale of 100 trillion parameters.

【15】 Super-resolving Dark Matter Halos using Generative Deep Learning 标题：基于产生式深度学习的超分辨暗物质晕 链接：https://arxiv.org/abs/2111.06393

作者：David Schaurecker,Yin Li,Jeremy Tinker,Shirley Ho,Alexandre Refregier 机构：Institute for Particle Physics and Astrophysics, ETH Zurich, Zurich, Center for Computational Astrophysics, Flatiron Institute - Simons Foundation, New York City NY 备注：9 pages, 8 figures 摘要：基于卷积神经网络（CNN）的生成性深度学习方法为预测宇宙学中的非线性结构提供了一个很好的工具。在这项工作中，我们预测高分辨率暗物质晕从大规模，低分辨率暗物质只模拟。这是通过将共享相同宇宙学、初始条件和盒子大小的模拟的较低分辨率场映射到较高分辨率密度场来实现的。为了将结构分解为质量分辨率增加8倍的因子，我们使用了U-Net的变化和条件GAN，生成的输出在视觉上和统计上与高分辨率目标非常匹配。这表明，我们的方法可以通过低分辨率模拟在Gpc/h盒尺寸上创建高分辨率密度输出，而计算工作量可以忽略不计。 摘要：Generative deep learning methods built upon Convolutional Neural Networks (CNNs) provide a great tool for predicting non-linear structure in cosmology. In this work we predict high resolution dark matter halos from large scale, low resolution dark matter only simulations. This is achieved by mapping lower resolution to higher resolution density fields of simulations sharing the same cosmology, initial conditions and box-sizes. To resolve structure down to a factor of 8 increase in mass resolution, we use a variation of U-Net with a conditional GAN, generating output that visually and statistically matches the high resolution target extremely well. This suggests that our method can be used to create high resolution density output over Gpc/h box-sizes from low resolution simulations with negligible computational effort.

【16】 Quantum Model-Discovery 标题：量子模型--发现 链接：https://arxiv.org/abs/2111.06376

作者：Niklas Heim,Atiyo Ghosh,Oleksandr Kyriienko,Vincent E. Elfving 机构：Qu & Co B.V., PO Box , AW, Amsterdam, The Netherlands, Artificial Intelligence Center, Czech Technical University, Prague, CZ , Department of Physics and Astronomy, University of Exeter, Stocker Road, Exeter EX,QL, United Kingdom 备注：first version, 18 pages, 6 figures 摘要：量子计算有望加速科学和工程中一些最具挑战性的问题。量子算法已经被提出，在从化学到物流优化的应用中显示出理论优势。科学和工程中出现的许多问题可以改写为一组微分方程。用于求解微分方程的量子算法在容错量子计算领域显示出可证明的优势，在容错量子计算领域，深度和广度的量子电路可以有效地求解偏微分方程（PDE）等大型线性系统。最近，也有人提出了用变分方法来求解非线性偏微分方程（PDE）的方法。最有希望的通用方法之一是基于科学机器学习领域中解决偏微分方程的最新发展。我们将短期量子计算机的适用性扩展到更一般的科学机器学习任务，包括从测量数据集中发现微分方程。我们使用可微量子电路（DQCs）求解由算符库参数化的方程，并对数据和方程的组合进行回归。我们的结果表明，在经典和量子机器学习方法之间的接口上，量子模型发现（QMoD）是一条有前途的道路。我们展示了在不同的系统上使用QMoD成功地进行参数推断和方程发现，包括一个二阶常微分方程和一个非线性偏微分方程。 摘要：Quantum computing promises to speed up some of the most challenging problems in science and engineering. Quantum algorithms have been proposed showing theoretical advantages in applications ranging from chemistry to logistics optimization. Many problems appearing in science and engineering can be rewritten as a set of differential equations. Quantum algorithms for solving differential equations have shown a provable advantage in the fault-tolerant quantum computing regime, where deep and wide quantum circuits can be used to solve large linear systems like partial differential equations (PDEs) efficiently. Recently, variational approaches to solving non-linear PDEs also with near-term quantum devices were proposed. One of the most promising general approaches is based on recent developments in the field of scientific machine learning for solving PDEs. We extend the applicability of near-term quantum computers to more general scientific machine learning tasks, including the discovery of differential equations from a dataset of measurements. We use differentiable quantum circuits (DQCs) to solve equations parameterized by a library of operators, and perform regression on a combination of data and equations. Our results show a promising path to Quantum Model Discovery (QMoD), on the interface between classical and quantum machine learning approaches. We demonstrate successful parameter inference and equation discovery using QMoD on different systems including a second-order, ordinary differential equation and a non-linear, partial differential equation.

【17】 On the Equivalence between Neural Network and Support Vector Machine 标题：论神经网络与支持向量机的等价性 链接：https://arxiv.org/abs/2111.06063

作者：Yilan Chen,Wei Huang,Lam M. Nguyen,Tsui-Wei Weng 机构：Computer Science and Engineering, University of California San Diego, La Jolla, CA, Engineering and Information Technology, University of Technology Sydney, Ultimo, Australia, IBM Research, Thomas J. Watson Research Center, Yorktown Heights, NY 备注：35th Conference on Neural Information Processing Systems (NeurIPS 2021) 摘要：最近的研究表明，通过梯度下降训练的无限宽神经网络（NN）的动力学可以用神经切线核（NTK）\citep{jacot2018neural}来表征。在平方损失下，通过梯度下降以无限小的学习率训练的无限宽NN等价于具有NTK\citep{arora2019exact}的核回归。然而，目前已知的等价性仅适用于岭回归，而NN与其他核机器（KMs），例如支持向量机（SVM）之间的等价性仍然未知。因此，在这项工作中，我们建议建立神经网络和支持向量机之间的等价性，特别是通过软边缘损失训练无限宽神经网络和通过次梯度下降训练NTK的标准软边缘支持向量机。我们的主要理论结果包括：建立了NN与一系列具有有限宽度边界的$\ell_2$正则化KMs之间的等价性，这是以前的工作所不能处理的，并且表明由此类正则化损失函数训练的每个有限宽度NN约为一KM。此外，我们还证明了我们的理论可以实现三个实际应用，包括（i）通过相应的知识管理实现神经网络的泛化界；（ii）无限宽NN的{非平凡}鲁棒性证书（而现有的鲁棒性验证方法将提供空洞的边界）；（iii）本质上比以前的核回归更稳健的无限宽NNs。我们的实验代码可在\url获取{https://github.com/leslie-CH/equiv-nn-svm}. 摘要：Recent research shows that the dynamics of an infinitely wide neural network (NN) trained by gradient descent can be characterized by Neural Tangent Kernel (NTK) \citep{jacot2018neural}. Under the squared loss, the infinite-width NN trained by gradient descent with an infinitely small learning rate is equivalent to kernel regression with NTK \citep{arora2019exact}. However, the equivalence is only known for ridge regression currently \citep{arora2019harnessing}, while the equivalence between NN and other kernel machines (KMs), e.g. support vector machine (SVM), remains unknown. Therefore, in this work, we propose to establish the equivalence between NN and SVM, and specifically, the infinitely wide NN trained by soft margin loss and the standard soft margin SVM with NTK trained by subgradient descent. Our main theoretical results include establishing the equivalence between NN and a broad family of $\ell_2$ regularized KMs with finite-width bounds, which cannot be handled by prior work, and showing that every finite-width NN trained by such regularized loss functions is approximately a KM. Furthermore, we demonstrate our theory can enable three practical applications, including (i) \textit{non-vacuous} generalization bound of NN via the corresponding KM; (ii) \textit{non-trivial} robustness certificate for the infinite-width NN (while existing robustness verification methods would provide vacuous bounds); (iii) intrinsically more robust infinite-width NNs than those from previous kernel regression. Our code for the experiments are available at \url{https://github.com/leslie-CH/equiv-nn-svm}.

【18】 Exponential separations between learning with and without quantum memory 标题：有量子记忆学习与无量子记忆学习之间的指数分离 链接：https://arxiv.org/abs/2111.05881

作者：Sitan Chen,Jordan Cotler,Hsin-Yuan Huang,Jerry Li 机构：UC Berkeley, Harvard University, Caltech, Microsoft Research 备注：77 pages, 2 figures, many diagrams; accepted to FOCS 2021 摘要：我们研究量子记忆对于学习量子系统和动力学性质的能力，这在物理和化学中具有重要意义。许多最先进的学习算法需要访问额外的外部量子内存。虽然这样的量子内存不是先验的，但在许多情况下，不使用量子内存的算法比使用量子内存的算法需要更多的数据。我们表明，这种权衡是广泛的学习问题所固有的。我们的结果包括以下内容：（1）我们表明，要对$n$-量子位状态rho和$M$可观测值执行阴影层析，任何没有量子内存的算法在最坏情况下都需要$\Omega（\min（M，2^n））$个rho样本。对于对数因子，这与[HKP20]的上限相匹配，并完全解决了[Aar18，AR19]中的一个未决问题。（2） 我们在有量子存储器和没有量子存储器的算法之间建立指数分离，用于纯度测试、区分置乱和去极化演化，以及揭示物理动力学中的对称性。我们的分离改进和推广了[ACQ21]之前的工作，允许使用更广泛的算法类，而不需要量子内存。（3） 我们给出了量子存储器和样本复杂性之间的第一个折衷。我们证明了，为了估计所有$n$-量子位泡利可观测值的绝对值，具有$k<n$量子位量子内存的算法至少需要$\Omega（2^{（n-k）/3}）$样本，但有一种使用$n$-量子位量子内存的算法只需要$O（n）$样本。我们展示的分离足够大，并且可能已经很明显，例如，对于几十个量子位。这为展示使用量子内存学习算法的真实优势提供了具体途径。 摘要：We study the power of quantum memory for learning properties of quantum systems and dynamics, which is of great importance in physics and chemistry. Many state-of-the-art learning algorithms require access to an additional external quantum memory. While such a quantum memory is not required a priori, in many cases, algorithms that do not utilize quantum memory require much more data than those which do. We show that this trade-off is inherent in a wide range of learning problems. Our results include the following: (1) We show that to perform shadow tomography on an $n$-qubit state rho with $M$ observables, any algorithm without quantum memory requires $\Omega(\min(M, 2^n))$ samples of rho in the worst case. Up to logarithmic factors, this matches the upper bound of [HKP20] and completely resolves an open question in [Aar18, AR19]. (2) We establish exponential separations between algorithms with and without quantum memory for purity testing, distinguishing scrambling and depolarizing evolutions, as well as uncovering symmetry in physical dynamics. Our separations improve and generalize prior work of [ACQ21] by allowing for a broader class of algorithms without quantum memory. (3) We give the first tradeoff between quantum memory and sample complexity. We prove that to estimate absolute values of all $n$-qubit Pauli observables, algorithms with $k < n$ qubits of quantum memory require at least $\Omega(2^{(n-k)/3})$ samples, but there is an algorithm using $n$-qubit quantum memory which only requires $O(n)$ samples. The separations we show are sufficiently large and could already be evident, for instance, with tens of qubits. This provides a concrete path towards demonstrating real-world advantage for learning algorithms with quantum memory.

其他(18篇)

【1】 Stationary Behavior of Constant Stepsize SGD Type Algorithms: An Asymptotic Characterization 标题：常步长SGD型算法的平稳行为：一个渐近特征 链接：https://arxiv.org/abs/2111.06328

作者：Zaiwei Chen,Shancong Mou,Siva Theja Maguluri 机构：‡ 1 Geogia Institute of Technology 摘要：随机逼近（SA）和随机梯度下降（SGD）算法是现代机器学习算法的工作马。由于收敛速度快，它们的恒定步长变量在实践中是首选的。然而，常步长随机迭代算法不是渐近收敛到最优解，而是具有平稳分布，这通常不能用解析方法描述。在这项工作中，我们研究了适当比例的平稳分布在常数步长为零时的渐近行为。具体地，我们考虑以下三个设置：（1）具有光滑和强凸目标的SGD算法，（2）涉及Hurwitz矩阵的线性SA算法，和（3）涉及压缩算子的非线性SA算法。当迭代按$1/\sqrt{\alpha}$缩放时，其中$\alpha$是常数步长，我们证明了极限缩放平稳分布是一个积分方程的解。在该方程的唯一性假设下（在某些情况下可以删除），我们进一步将极限分布描述为高斯分布，其协方差矩阵是合适的Lyapunov方程的唯一解。对于这些情况以外的SA算法，我们的数值实验表明，与中心极限定理类型的结果不同：（1）标度因子不必为$1/\sqrt{\alpha}$，以及（2）极限分布不必为高斯分布。在数值研究的基础上，我们提出了一个确定正确标度因子的公式，并与Euler-Maruyama离散格式进行了深入的联系，以逼近随机微分方程。 摘要：Stochastic approximation (SA) and stochastic gradient descent (SGD) algorithms are work-horses for modern machine learning algorithms. Their constant stepsize variants are preferred in practice due to fast convergence behavior. However, constant step stochastic iterative algorithms do not converge asymptotically to the optimal solution, but instead have a stationary distribution, which in general cannot be analytically characterized. In this work, we study the asymptotic behavior of the appropriately scaled stationary distribution, in the limit when the constant stepsize goes to zero. Specifically, we consider the following three settings: (1) SGD algorithms with smooth and strongly convex objective, (2) linear SA algorithms involving a Hurwitz matrix, and (3) nonlinear SA algorithms involving a contractive operator. When the iterate is scaled by $1/\sqrt{\alpha}$, where $\alpha$ is the constant stepsize, we show that the limiting scaled stationary distribution is a solution of an integral equation. Under a uniqueness assumption (which can be removed in certain settings) on this equation, we further characterize the limiting distribution as a Gaussian distribution whose covariance matrix is the unique solution of a suitable Lyapunov equation. For SA algorithms beyond these cases, our numerical experiments suggest that unlike central limit theorem type results: (1) the scaling factor need not be $1/\sqrt{\alpha}$, and (2) the limiting distribution need not be Gaussian. Based on the numerical study, we come up with a formula to determine the right scaling factor, and make insightful connection to the Euler-Maruyama discretization scheme for approximating stochastic differential equations.

【2】 AlphaDDA: game artificial intelligence with dynamic difficulty adjustment using AlphaZero 标题：AlphaDDA：利用AlphaZero实现难度动态调整的游戏人工智能 链接：https://arxiv.org/abs/2111.06266

作者：Kazuhisa Fujita 机构：Komatsu University,-, Doihara-Machi, Komatsu, Ishikawa, Japan ,-, University of Electro-Communications,-,-, Chofu-gaoka, Chofu, Tokyo, Japan, Corresponding author: 摘要：人工智能（AI）玩家在围棋、国际象棋和奥赛罗（Reversi）等游戏中获得了超人技能。换句话说，AI玩家作为人类玩家的对手变得过于强大。然后，我们就不会喜欢和AI玩家玩棋盘游戏了。为了娱乐人类玩家，AI玩家需要自动平衡其技能与人类玩家的技能。为了解决这个问题，我提出了AlphaDDA，一个基于AlphaZero的具有动态难度调整的AI玩家。AlphaDDA由深度神经网络（DNN）和类似AlphaZero的蒙特卡罗树搜索组成。AlphaDDA使用DNN仅从棋盘状态估计游戏状态的值，并根据该值更改其技能。AlphaDDA可以仅使用游戏状态调整AlphaDDA的技能，而无需事先了解对手。在这项研究中，AlphaDDA播放Connect4，6x6 Otherlo，这是使用6x6大小板的Otherlo，以及Otherlo和其他AI代理。其他人工智能代理包括AlphaZero、Monte Carlo树搜索、Minimax算法和随机玩家。这项研究表明，AlphaDDA实现了和其他AI代理（随机玩家除外）的技能平衡。AlphaDDA的DDA能力来自于对游戏状态值的精确估计。我们将能够在任何游戏中使用AlphaDDA方法，因为DNN可以从状态估计值。 摘要：An artificial intelligence (AI) player has obtained superhuman skill for games like Go, Chess, and Othello (Reversi). In other words, the AI player becomes too strong as an opponent of human players. Then, we will not enjoy playing board games with the AI player. In order to entertain human players, the AI player is required to balance its skill with the human player's one automatically. To address this issue, I propose AlphaDDA, an AI player with dynamic difficulty adjustment based on AlphaZero. AlphaDDA consists of a deep neural network (DNN) and Monte Carlo tree search like AlphaZero. AlphaDDA estimates the value of the game state form only the board state using the DNN and changes its skill according to the value. AlphaDDA can adjust AlphaDDA's skill using only the state of a game without prior knowledge about an opponent. In this study, AlphaDDA plays Connect4, 6x6 Othello, which is Othello using a 6x6 size board, and Othello with the other AI agents. The other AI agents are AlphaZero, Monte Carlo tree search, Minimax algorithm, and a random player. This study shows that AlphaDDA achieves to balance its skill with the other AI agents except for a random player. AlphaDDA's DDA ability is derived from the accurate estimation of the value from the state of a game. We will be able to use the approach of AlphaDDA for any games in that the DNN can estimate the value from the state.

【3】 Branch and Bound in Mixed Integer Linear Programming Problems: A Survey of Techniques and Trends 标题：混合整数线性规划问题的分枝定界技术及发展趋势 链接：https://arxiv.org/abs/2111.06257

作者：Lingying Huang,Xiaomeng Chen,Wei Huo,Jiazheng Wang,Fan Zhang,Bo Bai,Ling Shi 机构：Department of Electronic Engineering, HKUST, Clear Water Bay, Kowloon, Hong Kong, Theory Lab, Huawei Hong Kong Research Centre, Hong Kong SAR, China 备注：Preprint submitted to Discrete Optimization 摘要：在本文中，我们回顾了现有文献，研究了一般分枝定界（B&B）算法中四个关键组件的不同方法和算法，即分支变量选择、节点选择、节点修剪和切割平面选择。然而，B&B算法的复杂度总是随着决策变量维数的增加呈指数增长。为了提高B&B算法的速度，最近在该算法中引入了学习技术。我们进一步调查了机器学习如何用于改进B&B算法中的四个关键组件。一般来说，有监督的学习方法有助于生成模仿专家但显著提高速度的策略。无监督学习方法有助于根据特征选择不同的方法。此外，在充分训练和有监督初始化的情况下，经过强化学习训练的模型可以优于专家策略。我们的调查总结了不同算法之间的详细比较。最后，我们在文献中讨论了进一步加速和改进算法的一些未来研究方向。 摘要：In this paper, we surveyed the existing literature studying different approaches and algorithms for the four critical components in the general branch and bound (B&B) algorithm, namely, branching variable selection, node selection, node pruning, and cutting-plane selection. However, the complexity of the B&B algorithm always grows exponentially with respect to the increase of the decision variable dimensions. In order to improve the speed of B&B algorithms, learning techniques have been introduced in this algorithm recently. We further surveyed how machine learning can be used to improve the four critical components in B&B algorithms. In general, a supervised learning method helps to generate a policy that mimics an expert but significantly improves the speed. An unsupervised learning method helps choose different methods based on the features. In addition, models trained with reinforcement learning can beat the expert policy, given enough training and a supervised initialization. Detailed comparisons between different algorithms have been summarized in our survey. Finally, we discussed some future research directions to accelerate and improve the algorithms further in the literature.

【4】 BOiLS: Bayesian Optimisation for Logic Synthesis 标题：BOILS：逻辑综合的贝叶斯优化 链接：https://arxiv.org/abs/2111.06178

作者：Antoine Grosnit,Cedric Malherbe,Rasul Tutunov,Xingchen Wan,Jun Wang,Haitham Bou Ammar 机构：Huawei Noah’s Ark Lab, University College London 摘要：在逻辑综合过程中优化电路的结果质量（QoR）是一项艰巨的挑战，需要探索指数大小的搜索空间。虽然专家设计的操作有助于发现有效序列，但逻辑电路复杂性的增加有利于自动化程序。受机器学习成功的启发，研究人员将深度学习和强化学习应用于逻辑综合应用。无论多么成功，这些技术都面临着样本复杂度高的问题，阻碍了广泛采用。为了实现高效和可扩展的解决方案，我们提出了BOiLS，这是第一个采用现代贝叶斯优化来导航合成操作空间的算法。BOiLS不需要人工干预，通过新颖的高斯过程内核和信任区域约束的获取，有效地权衡了探索与开发。在EPFL基准测试的一组实验中，我们展示了BOiLS在样本效率和QoR值方面优于最新技术。 摘要：Optimising the quality-of-results (QoR) of circuits during logic synthesis is a formidable challenge necessitating the exploration of exponentially sized search spaces. While expert-designed operations aid in uncovering effective sequences, the increase in complexity of logic circuits favours automated procedures. Inspired by the successes of machine learning, researchers adapted deep learning and reinforcement learning to logic synthesis applications. However successful, those techniques suffer from high sample complexities preventing widespread adoption. To enable efficient and scalable solutions, we propose BOiLS, the first algorithm adapting modern Bayesian optimisation to navigate the space of synthesis operations. BOiLS requires no human intervention and effectively trades-off exploration versus exploitation through novel Gaussian process kernels and trust-region constrained acquisitions. In a set of experiments on EPFL benchmarks, we demonstrate BOiLS's superior performance compared to state-of-the-art in terms of both sample efficiency and QoR values.

【5】 Reducing Data Complexity using Autoencoders with Class-informed Loss Functions 标题：使用具有类通知丢失函数的自动编码器降低数据复杂度 链接：https://arxiv.org/abs/2111.06142

作者：David Charte,Francisco Charte,Francisco Herrera 备注：This paper has been accepted for publication by IEEE Transactions on Pattern Analysis and Machine Intelligence 摘要：机器学习应用中的可用数据正变得越来越复杂，这是由于更高的维度和困难的类。根据类别重叠、可分性或边界形状以及组形态，有各种各样的方法来测量标记数据的复杂性。许多技术可以转换数据以找到更好的特征，但很少有技术专门用于降低数据复杂性。大多数数据转换方法主要处理维度方面，而忽略类标签中的可用信息，这些信息在类比较复杂时可能会很有用。本文提出了一种基于自动编码器的复杂度降低方法，使用类标签来通知损失函数生成的变量的充分性。这导致了三种不同的新特性学习器，Scorer、Skaler和Slicer。它们分别基于Fisher判别比、Kullback-Leibler散度和最小二乘支持向量机。它们可以作为二元分类问题的预处理阶段。对27个数据集和一系列复杂度和分类指标的全面实验表明，基于类的自动编码器的性能优于其他4种流行的无监督特征提取技术，尤其是当最终目标是将数据用于分类任务时。 摘要：Available data in machine learning applications is becoming increasingly complex, due to higher dimensionality and difficult classes. There exists a wide variety of approaches to measuring complexity of labeled data, according to class overlap, separability or boundary shapes, as well as group morphology. Many techniques can transform the data in order to find better features, but few focus on specifically reducing data complexity. Most data transformation methods mainly treat the dimensionality aspect, leaving aside the available information within class labels which can be useful when classes are somehow complex. This paper proposes an autoencoder-based approach to complexity reduction, using class labels in order to inform the loss function about the adequacy of the generated variables. This leads to three different new feature learners, Scorer, Skaler and Slicer. They are based on Fisher's discriminant ratio, the Kullback-Leibler divergence and least-squares support vector machines, respectively. They can be applied as a preprocessing stage for a binary classification problem. A thorough experimentation across a collection of 27 datasets and a range of complexity and classification metrics shows that class-informed autoencoders perform better than 4 other popular unsupervised feature extraction techniques, especially when the final objective is using the data for a classification task.

【6】 Solving Multi-Arm Bandit Using a Few Bits of Communication 标题：用几个通信比特求解多臂盗贼 链接：https://arxiv.org/abs/2111.06067

作者：Osama A. Hanna,Lin F. Yang,Christina Fragouli 机构：†University of California, Los Angeles 摘要：多武装匪徒（MAB）问题是一个主动学习框架，旨在通过连续观察奖励从一组行动中选择最佳行动。最近，它在无线网络上的许多应用中变得流行，在这些应用中，通信限制可能会形成瓶颈。现有工程通常无法解决此问题，在某些应用中可能变得不可行。在本文中，我们通过优化分布式代理收集的奖励的通信来解决通信问题。通过提供几乎匹配的上下界，我们严格描述了每个奖励所需的位数，以便学习者准确地学习而不会产生额外的遗憾。特别是，我们建立了一种通用的奖赏量化算法QuBan，它可以应用于任何（无遗憾）MAB算法之上，以形成一种新的通信高效的对应算法，该算法每次迭代只需要发送少量（低至3）位，同时保持相同的遗憾边界。我们的下界是通过从次高斯分布构造硬实例来建立的。数值实验进一步证实了我们的理论。 摘要：The multi-armed bandit (MAB) problem is an active learning framework that aims to select the best among a set of actions by sequentially observing rewards. Recently, it has become popular for a number of applications over wireless networks, where communication constraints can form a bottleneck. Existing works usually fail to address this issue and can become infeasible in certain applications. In this paper we address the communication problem by optimizing the communication of rewards collected by distributed agents. By providing nearly matching upper and lower bounds, we tightly characterize the number of bits needed per reward for the learner to accurately learn without suffering additional regret. In particular, we establish a generic reward quantization algorithm, QuBan, that can be applied on top of any (no-regret) MAB algorithm to form a new communication-efficient counterpart, that requires only a few (as low as 3) bits to be sent per iteration while preserving the same regret bound. Our lower bound is established via constructing hard instances from a subgaussian distribution. Our theory is further corroborated by numerically experiments.

【7】 Edge-Cloud Polarization and Collaboration: A Comprehensive Survey 标题：边云极化与协作：综述 链接：https://arxiv.org/abs/2111.06061

作者：Jiangchao Yao,Shengyu Zhang,Yang Yao,Feng Wang,Jianxin Ma,Jianwei Zhang,Yunfei Chu,Luo Ji,Kunyang Jia,Tao Shen,Anpeng Wu,Fengda Zhang,Ziqi Tan,Kun Kuang,Chao Wu,Fei Wu,Jingren Zhou,Hongxia Yang 机构： Wuare with Zhengjia University 备注：20 pages. Under Submission. arXiv admin note: text overlap with arXiv:2103.13630 by other authors 摘要：受云计算深度学习的巨大成功和边缘芯片的快速发展的影响，人工智能（AI）的研究已经转向两种计算范式，即云计算和边缘计算。近年来，我们见证了在云服务器上开发更先进的人工智能模型的重大进展，这些模型的创新（如Transformer、预训练家庭）、训练数据的爆炸性增长和计算能力的飞速发展，超过了传统的深度学习模型。然而，边缘计算，特别是边缘和云协同计算，由于资源受限的物联网场景和部署的算法非常有限，因此仍处于宣布其成功的初级阶段。在本次调查中，我们对云计算和边缘人工智能进行了系统回顾。具体来说，我们是第一个为云和边缘建模建立协作学习机制的人，并对支持这种机制的体系结构进行了全面审查。我们还讨论了一些正在进行的高级边缘人工智能主题的潜力和实践经验，包括预训练模型、图形神经网络和强化学习。最后，我们讨论了这一领域的前景和挑战。 摘要：Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the computing paradigms, i.e., cloud computing and edge computing. In recent years, we have witnessed significant progress in developing more advanced AI models on cloud servers that surpass traditional deep learning models owing to model innovations (e.g., Transformers, Pretrained families), explosion of training data and soaring computing capabilities. However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed. In this survey, we conduct a systematic review for both cloud and edge AI. Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism. We also discuss potentials and practical experiences of some on-going advanced edge AI topics including pretraining models, graph neural networks and reinforcement learning. Finally, we discuss the promising directions and challenges in this field.

【8】 Constrained Stochastic Submodular Maximization with State-Dependent Costs 标题：费用依赖于状态的约束随机子模极大化 链接：https://arxiv.org/abs/2111.06037

作者：Shaojie Tang 机构：University of Texas at Dallas 摘要：本文研究了具有状态相关代价的约束随机子模最大化问题。我们问题的输入是一组项目，其状态（即，一个项目的边际贡献和成本）是根据已知的概率分布得出的。了解项目实现状态的唯一方法是选择该项目。我们考虑两个约束，即，EMPH{{Ne}}和\EMPH{{Le}}约束。回想一下，每个项目都有一个依赖于状态的成本，内部约束规定所有选定项目的总\emph{realized}成本不得超过给定的预算。因此，内部约束依赖于状态。另一方面，外部约束与状态无关。它可以表示为选定项目集的向下闭合族，而不管其状态如何。我们的目标是在内外约束条件下使目标函数最大化。在假设成本越大表示效用越大的情况下，我们给出了该问题的一个常数近似解。 摘要：In this paper, we study the constrained stochastic submodular maximization problem with state-dependent costs. The input of our problem is a set of items whose states (i.e., the marginal contribution and the cost of an item) are drawn from a known probability distribution. The only way to know the realized state of an item is to select that item. We consider two constraints, i.e., \emph{inner} and \emph{outer} constraints. Recall that each item has a state-dependent cost, and the inner constraint states that the total \emph{realized} cost of all selected items must not exceed a give budget. Thus, inner constraint is state-dependent. The outer constraint, one the other hand, is state-independent. It can be represented as a downward-closed family of sets of selected items regardless of their states. Our objective is to maximize the objective function subject to both inner and outer constraints. Under the assumption that larger cost indicates larger "utility", we present a constant approximate solution to this problem.

【9】 Causal KL: Evaluating Causal Discovery 标题：因果KL：评估因果发现 链接：https://arxiv.org/abs/2111.06029

作者：Rodney T. O'Donnell,Kevin B. Korb,Lloyd Allison 机构：School of Information Technology, Monash University, Clayton, Vic, Australia 备注：26 pages 摘要：使用人工数据评估因果模型发现的两个最常用标准是编辑距离和Kullback-Leibler散度，从真实模型到学习模型进行测量。这两个指标最大限度地奖励了真正的模型。然而，我们认为，在判断错误模型的相对优点时，他们都没有足够的辨别力。例如，“编辑距离”无法区分强概率依赖和弱概率依赖。另一方面，KL分歧对所有统计上等价的模型都给予同等的奖励，而不管它们的因果关系不同。我们提出了一种扩展的KL散度，我们称之为因果KL（CKL），它考虑了区分观测等效模型的因果关系。结果显示了三种CKL变体，表明因果KL在实践中效果良好。 摘要：The two most commonly used criteria for assessing causal model discovery with artificial data are edit-distance and Kullback-Leibler divergence, measured from the true model to the learned model. Both of these metrics maximally reward the true model. However, we argue that they are both insufficiently discriminating in judging the relative merits of false models. Edit distance, for example, fails to distinguish between strong and weak probabilistic dependencies. KL divergence, on the other hand, rewards equally all statistically equivalent models, regardless of their different causal claims. We propose an augmented KL divergence, which we call Causal KL (CKL), which takes into account causal relationships which distinguish between observationally equivalent models. Results are presented for three variants of CKL, showing that Causal KL works well in practice.

【10】 HMD-AMP: Protein Language-Powered Hierarchical Multi-label Deep Forest for Annotating Antimicrobial Peptides 标题：HMD-AMP：基于蛋白质语言的层次化多标签深层森林抗菌肽标注 链接：https://arxiv.org/abs/2111.06023

作者：Qinze Yu,Zhihang Dong,Xingyu Fan,Licheng Zong,Yu Li 机构：Department of Computer Science and Engineering, CUHK, Hong Kong SAR, China, The CUHK Shenzhen Research Institute, Hi-Tech Park, Nanshan, Shenzhen, China, University of Electronic Science and Technology of China, Chengdu, Sichuan, China 备注：16 pages 8 figures 摘要：确定抗菌肽的靶点是研究先天免疫反应和对抗抗生素耐药性以及更广泛的精确医学和公共卫生的一个基本步骤。已经对统计和计算方法进行了广泛的研究，以确定（i）肽是抗菌肽（AMP）还是非AMP，以及（ii）这些序列对（革兰氏阳性、革兰氏阴性等）有效的靶点。尽管已有关于这个问题的深入学习方法，但大多数方法无法处理小型AMP类（抗虫、抗寄生虫等）。更重要的是，一些AMPS可以有多个目标，以前的方法没有考虑。在本研究中，我们通过收集和清理各种AMP数据库中的氨基酸，建立了一个多样化和全面的多标签蛋白质序列数据库。为了为小类数据集生成有效的表示和特征，我们利用了一个在2.5亿个蛋白质序列上训练的蛋白质语言模型。在此基础上，我们开发了一个端到端的分层多标签深林框架HMD-AMP，对AMP进行全面的注释。在识别了一个AMP之后，它进一步预测了AMP可以从11个可用类中有效杀死哪些目标。大量的实验表明，我们的框架在二元分类任务和多标签分类任务中都优于最新的模型，尤其是在次要类别上。该模型对减少的特征和小扰动具有鲁棒性，并产生了有希望的结果。我们相信HMD-AMP有助于未来湿实验室研究不同抗菌肽的固有结构特性，并为使用抗生素的精确医学奠定有希望的经验基础。 摘要：Identifying the targets of an antimicrobial peptide is a fundamental step in studying the innate immune response and combating antibiotic resistance, and more broadly, precision medicine and public health. There have been extensive studies on the statistical and computational approaches to identify (i) whether a peptide is an antimicrobial peptide (AMP) or a non-AMP and (ii) which targets are these sequences effective to (Gram-positive, Gram-negative, etc.). Despite the existing deep learning methods on this problem, most of them are unable to handle the small AMP classes (anti-insect, anti-parasite, etc.). And more importantly, some AMPs can have multiple targets, which the previous methods fail to consider. In this study, we build a diverse and comprehensive multi-label protein sequence database by collecting and cleaning amino acids from various AMP databases. To generate efficient representations and features for the small classes dataset, we take advantage of a protein language model trained on 250 million protein sequences. Based on that, we develop an end-to-end hierarchical multi-label deep forest framework, HMD-AMP, to annotate AMP comprehensively. After identifying an AMP, it further predicts what targets the AMP can effectively kill from eleven available classes. Extensive experiments suggest that our framework outperforms state-of-the-art models in both the binary classification task and the multi-label classification task, especially on the minor classes.The model is robust against reduced features and small perturbations and produces promising results. We believe HMD-AMP contributes to both the future wet-lab investigations of the innate structural properties of different antimicrobial peptides and build promising empirical underpinnings for precise medicine with antibiotics.

【11】 Agent Spaces 标题：代理空间 链接：https://arxiv.org/abs/2111.06005

作者：John C. Raisbeck,Matthew W. Allen,Hakho Lee 机构：Center for Systems Biology, Massachusetts General Hospital, Boston, Massachusetts 备注：40 pages, 1 fiture 摘要：探索是强化学习中最重要的任务之一，但在动态规划范式中，除了有限问题之外，它没有得到很好的定义（见第2.4小节）。我们提供了一个可应用于任何在线学习方法的探索的重新解释。我们从一个新的方向来探索，从而得出这个定义。在发现用动态规划求解简单马尔可夫决策过程的探索概念不再广泛适用之后，我们重新审视了探索。我们没有扩展动态勘探程序的目的，而是扩展了它们的手段。也就是说，我们将修改代理的行为定义为探索性的，而不是重复地对流程中可能的每个状态-动作对进行采样。由此产生的探索定义可以应用于无限问题和非动态学习方法，这是探索的动态概念所不能容忍的。为了理解agent的修改影响学习的方式，我们描述了agent集合上的一种新结构：距离集合（见脚注7）$d_{a}\ in a$，它代表了过程中每个agent可能的视角。利用这些距离，我们定义了一个拓扑，并证明了强化学习中的许多重要结构在agent空间中的收敛所诱导的拓扑下表现良好。 摘要：Exploration is one of the most important tasks in Reinforcement Learning, but it is not well-defined beyond finite problems in the Dynamic Programming paradigm (see Subsection 2.4). We provide a reinterpretation of exploration which can be applied to any online learning method. We come to this definition by approaching exploration from a new direction. After finding that concepts of exploration created to solve simple Markov decision processes with Dynamic Programming are no longer broadly applicable, we reexamine exploration. Instead of extending the ends of dynamic exploration procedures, we extend their means. That is, rather than repeatedly sampling every state-action pair possible in a process, we define the act of modifying an agent to itself be explorative. The resulting definition of exploration can be applied in infinite problems and non-dynamic learning methods, which the dynamic notion of exploration cannot tolerate. To understand the way that modifications of an agent affect learning, we describe a novel structure on the set of agents: a collection of distances (see footnote 7) $d_{a} \in A$, which represent the perspectives of each agent possible in the process. Using these distances, we define a topology and show that many important structures in Reinforcement Learning are well behaved under the topology induced by convergence in the agent space.

【12】 A study on Channel Popularity in Twitch 标题：“Twitch”频道热度研究 链接：https://arxiv.org/abs/2111.05939

作者：Ha Le,Junming Wu,Louis Yu,Melissa Lynn 机构：Gustavus Adolphus College 摘要：在过去几十年中，互联网用户越来越需要在线主持实时活动，并与现场互动观众分享他们的体验。像Twitch这样的在线流媒体服务吸引了数以百万计的用户来流媒体和观看。关于在Twitch上预测拖缆受欢迎程度的研究很少。在这篇文章中，我们将探讨有助于拖缆普及的潜在因素。拖缆数据是在4周内使用Twitch的API通过一致跟踪收集的。收集每个用户的流媒体信息，如当前观众和关注者的数量、流的类型等。从结果中，我们发现流会话的频率、内容类型和流的长度是决定观众和订户流在会话期间可以获得多少收益的主要因素。 摘要：In the past few decades, there has been an increasing need for Internet users to host real time events online and to share their experiences with live, interactive audiences. Online streaming services like Twitch have attracted millions of users to stream and to spectate. There have been few studies about the prediction of streamers' popularity on Twitch. In this paper, we look at potential factors that can contribute to the popularity of streamers. Streamer data was collected through consistent tracking using Twitch's API during a 4 weeks period. Each user's streaming information such as the number of current viewers and followers, the genre of the stream etc., were collected. From the results, we found that the frequency of streaming sessions, the types of content and the length of the streams are major factors in determining how much viewers and subscribers streamers can gain during sessions.

【13】 A soft thumb-sized vision-based sensor with accurate all-round force perception 标题：一种具有准确全方位力感知的软拇指大小视觉传感器 链接：https://arxiv.org/abs/2111.05934

作者：Huanbo Sun,Katherine J. Kuchenbecker,Georg Martius 机构： Autonomous Learning Group, Max Planck Institute for Intelligent Systems, Tübingen, Germany., Haptic Intelligence Department, Max Planck Institute for Intelligent Systems, Stuttgart, Germany. 备注：1 table, 5 figures, 24 pages for the main manuscript. 5 tables, 12 figures, 27 pages for the supplementary material. 8 supplementary videos 摘要：基于视觉的触觉传感器由于价格合理的高分辨率摄像机和成功的计算机视觉技术，已成为机器人触摸的一种很有前途的方法。然而，它们的物理设计和提供的信息还不能满足实际应用的要求。我们提出了一种健壮、柔软、低成本、基于视觉、拇指大小的三维触觉传感器Insight：它在整个锥形传感表面上持续提供方向力分布图。该传感器围绕内置单目摄像头构建，只有一层弹性体模压在刚性框架上，以保证灵敏度、鲁棒性和软接触。此外，Insight是第一个使用准直器将光度立体光和结构光结合起来检测其易于更换的柔性外壳的三维变形的系统。力信息由深度神经网络推断，该网络将图像映射到三维接触力（法向和剪切）的空间分布。Insight的总体空间分辨率为0.4 mm，力大小精度约为0.03 N，力方向精度约为5度，范围为0.03-2 N，适用于具有不同接触面积的多个不同触点。所提出的硬件和软件设计概念可应用于各种机器人部件。 摘要：Vision-based haptic sensors have emerged as a promising approach to robotic touch due to affordable high-resolution cameras and successful computer-vision techniques. However, their physical design and the information they provide do not yet meet the requirements of real applications. We present a robust, soft, low-cost, vision-based, thumb-sized 3D haptic sensor named Insight: it continually provides a directional force-distribution map over its entire conical sensing surface. Constructed around an internal monocular camera, the sensor has only a single layer of elastomer over-molded on a stiff frame to guarantee sensitivity, robustness, and soft contact. Furthermore, Insight is the first system to combine photometric stereo and structured light using a collimator to detect the 3D deformation of its easily replaceable flexible outer shell. The force information is inferred by a deep neural network that maps images to the spatial distribution of 3D contact force (normal and shear). Insight has an overall spatial resolution of 0.4 mm, force magnitude accuracy around 0.03 N, and force direction accuracy around 5 degrees over a range of 0.03--2 N for numerous distinct contacts with varying contact area. The presented hardware and software design concepts can be transferred to a wide variety of robot parts.

【14】 ARISE: ApeRIodic SEmi-parametric Process for Efficient Markets without Periodogram and Gaussianity Assumptions 标题：RISE：无周期图和高斯假设的有效市场的非周期半参数过程 链接：https://arxiv.org/abs/2111.06222

作者：Shao-Qun Zhang,Zhi-Hua Zhou 机构：National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing , China 摘要：模仿和学习有效市场的长期记忆是机器学习和金融经济学对连续数据交互作用的一个基本问题。尽管这个问题很突出，但目前的治疗方法要么主要局限于启发式技术，要么主要依赖周期图或高斯假设。本文给出了研究有效市场的非周期半参数过程。该过程被描述为一些已知过程的无穷和函数，并采用非周期谱估计来确定关键超参数，因此具有建模具有长期记忆性、非平稳性和非周期谱的价格数据的能力和潜力。我们进一步从理论上证明了该过程具有均方收敛性、一致性和渐近正态性，没有周期图和高斯假设。在实践中，我们应用产生过程来确定现实世界市场的效率。此外，我们还提供了两种替代的应用：研究各种机器学习模型的长期记忆性和开发用于时间序列推断和预测的潜在状态空间模型。数值实验证实了本文方法的优越性。 摘要：Mimicking and learning the long-term memory of efficient markets is a fundamental problem in the interaction between machine learning and financial economics to sequential data. Despite the prominence of this issue, current treatments either remain largely limited to heuristic techniques or rely significantly on periodogram or Gaussianty assumptions. In this paper, we present the ApeRIodic SEmi-parametric (ARISE) process for investigating efficient markets. The ARISE process is formulated as an infinite-sum function of some known processes and employs the aperiodic spectrum estimation to determine the key hyper-parameters, thus possessing the power and potential of modeling the price data with long-term memory, non-stationarity, and aperiodic spectrum. We further theoretically show that the ARISE process has the mean-square convergence, consistency, and asymptotic normality without periodogram and Gaussianity assumptions. In practice, we apply the ARISE process to identify the efficiency of real-world markets. Besides, we also provide two alternative ARISE applications: studying the long-term memorability of various machine-learning models and developing a latent state-space model for inference and forecasting of time series. The numerical experiments confirm the superiority of our proposed approaches.

【15】 Tight bounds for minimum l1-norm interpolation of noisy data 标题：含噪数据最小L1范数插值的紧界 链接：https://arxiv.org/abs/2111.05987

作者：Guillaume Wang,Konstantin Donhauser,Fanny Yang 机构：ETH Zurich, Department of Computer Science, ETH AI Center 备注：29 pages, 1 figure 摘要：我们为最小$\ellu 1$-范数插值器的预测误差，即基追踪，提供了$\sigma^2/\log（d/n）$阶的匹配上界和下界。我们的结果在$d\gg n$时紧到可以忽略的项，并且是第一个暗示各向同性特征和稀疏地面真相的噪声最小范数插值的渐近一致性。我们的工作补充了关于最小$\ell_2$-范数插值的“良性过拟合”的文献，其中只有当特征有效地是低维时才能实现渐近一致性。 摘要：We provide matching upper and lower bounds of order $\sigma^2/\log(d/n)$ for the prediction error of the minimum $\ell_1$-norm interpolator, a.k.a. basis pursuit. Our result is tight up to negligible terms when $d \gg n$, and is the first to imply asymptotic consistency of noisy minimum-norm interpolation for isotropic features and sparse ground truths. Our work complements the literature on "benign overfitting" for minimum $\ell_2$-norm interpolation, where asymptotic consistency can be achieved only when the features are effectively low-dimensional.

【16】 SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision 标题：SyMetric：测量从视觉推断的学习哈密顿动力学的质量 链接：https://arxiv.org/abs/2111.05986

作者：Irina Higgins,Peter Wirnsberger,Andrew Jaegle,Aleksandar Botev 机构：DeepMind, London 摘要：最近提出的一类模型试图利用哈密顿力学提供的先验知识，从高维观测（如图像）中学习潜在动力学。虽然这些模型在机器人技术或自动驾驶等领域有着重要的潜在应用，但目前还没有很好的方法来评估它们的性能：现有的方法主要依赖于图像重建质量，而图像重建质量并不总是反映学习到的潜在动力学的质量。在这项工作中，我们根据经验强调了现有度量的问题，并开发了一组新的度量，包括一个二元指标，用于指示是否忠实地捕获了潜在的哈密顿动力学，我们称之为辛度量或符号度量。我们的方法利用了哈密顿动力学的已知特性，并且比重建误差更能区分模型捕捉潜在动力学的能力。利用对称性，我们确定了一组体系结构选择，显著提高了先前提出的从像素推断潜在动态的模型哈密顿生成网络（HGN）的性能。与原始HGN不同，新的HGN++能够在某些数据集上发现具有物理意义的延迟的可解释相空间。此外，它在13个数据集的不同范围内稳定地进行更长时间的展期，在时间上向前和向后产生基本上无限长的展期，而在数据集的一个子集上没有质量下降。 摘要：A recently proposed class of models attempts to learn latent dynamics from high-dimensional observations, like images, using priors informed by Hamiltonian mechanics. While these models have important potential applications in areas like robotics or autonomous driving, there is currently no good way to evaluate their performance: existing methods primarily rely on image reconstruction quality, which does not always reflect the quality of the learnt latent dynamics. In this work, we empirically highlight the problems with the existing measures and develop a set of new measures, including a binary indicator of whether the underlying Hamiltonian dynamics have been faithfully captured, which we call Symplecticity Metric or SyMetric. Our measures take advantage of the known properties of Hamiltonian dynamics and are more discriminative of the model's ability to capture the underlying dynamics than reconstruction error. Using SyMetric, we identify a set of architectural choices that significantly improve the performance of a previously proposed model for inferring latent dynamics from pixels, the Hamiltonian Generative Network (HGN). Unlike the original HGN, the new HGN++ is able to discover an interpretable phase space with physically meaningful latents on some datasets. Furthermore, it is stable for significantly longer rollouts on a diverse range of 13 datasets, producing rollouts of essentially infinite length both forward and backwards in time with no degradation in quality on a subset of the datasets.

【17】 Beyond Importance Scores: Interpreting Tabular ML by Visualizing Feature Semantics 标题：超越重要性分数：通过可视化要素语义来解释表格ML 链接：https://arxiv.org/abs/2111.05898

作者：Amirata Ghorbani,Dina Berenbaum,Maor Ivgi,Yuval Dafna,James Zou 机构：Stanford University, Demystify AI 摘要：随着机器学习（ML）的兴起，可解释性正成为一个活跃的研究课题模型更广泛地用于做出关键决策。表格数据是医疗保健和金融等多种应用中最常用的数据模式之一。许多用于表格数据的现有可解释性方法仅报告特征重要性得分——局部（每个示例）或全局（每个模型）--但它们不提供特征交互方式的解释或可视化。我们通过引入特征向量（专为表格数据集设计的一种新的全局可解释性方法）来解决这一局限性。除了提供特征重要性外，特征向量还通过intu发现特征之间固有的语义关系直观特征可视化技术。我们的系统实验通过将该方法应用于多个真实数据集，证明了该方法的经验效用。我们进一步提供了一个易于使用的特征向量Python包。 摘要：Interpretability is becoming an active research topic as machine learning (ML) models are more widely used to make critical decisions. Tabular data is one of the most commonly used modes of data in diverse applications such as healthcare and finance. Much of the existing interpretability methods used for tabular data only report feature-importance scores -- either locally (per example) or globally (per model) -- but they do not provide interpretation or visualization of how the features interact. We address this limitation by introducing Feature Vectors, a new global interpretability method designed for tabular datasets. In addition to providing feature-importance, Feature Vectors discovers the inherent semantic relationship among features via an intuitive feature visualization technique. Our systematic experiments demonstrate the empirical utility of this new method by applying it to several real-world datasets. We further provide an easy-to-use Python package for Feature Vectors.

【18】 A Hierarchy for Replica Quantum Advantage 标题：复制品量子优势的层次结构 链接：https://arxiv.org/abs/2111.05874

作者：Sitan Chen,Jordan Cotler,Hsin-Yuan Huang,Jerry Li 机构：Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA, USA, Simons Institute for the Theory of Computing, Berkeley, CA, USA, Society of Fellows, Harvard University, Cambridge, MA, USA 备注：3+17 pages, 2 figures 摘要：我们证明，如果同时对$n$-量子位态$\rho$的至多$k$副本进行纠缠测量，则$\rho$的一个属性至少需要$2^n/k^2$次测量才能学习。然而，如果我们可以对多个副本多项式（单位为$k，n$）进行纠缠测量，那么同样的属性只需要一次测量就可以了解。由于上述情况适用于每个正整数$k$，因此我们获得了一个任务层次结构，需要高效地执行越来越多的副本。我们引入了一种强大的证明技术来建立我们的结果，并利用它来为测试量子态的混合性提供新的边界。 摘要：We prove that given the ability to make entangled measurements on at most $k$ replicas of an $n$-qubit state $\rho$ simultaneously, there is a property of $\rho$ which requires at least order $2^n / k^2$ measurements to learn. However, the same property only requires one measurement to learn if we can make an entangled measurement over a number of replicas polynomial in $k, n$. Because the above holds for each positive integer $k$, we obtain a hierarchy of tasks necessitating progressively more replicas to be performed efficiently. We introduce a powerful proof technique to establish our results, and also use this to provide new bounds for testing the mixedness of a quantum state.