机器学习学术论文参考[02.03]

cs.LG 方向，今日共计100篇

【1】 Report of the Workshop on Program Synthesis for Scientific Computing

标题：科学计算程序综合研讨会报告

作者：Hal Finkel,Ignacio Laguna

备注：29 pages, workshop website: this https URL

链接：https://arxiv.org/abs/2102.01687

【2】 Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network  Optimization

标题：保持梯度流动：利用梯度流研究稀疏网络优化

作者：Kale-ab Tessera,Sara Hooker,Benjamin Rosman

机构：University of the Witwatersrand, Google Brain

链接：https://arxiv.org/abs/2102.01670

【3】 Online Learning with Simple Predictors and a Combinatorial  Characterization of Minimax in 0/1 Games

标题：具有简单预测因子的在线学习与0/1对策中极大极小的组合刻画

作者：Steve Hanneke,Roi Livni,Shay Moran

机构：Toyota Technological Institute at Chicago, Tel Aviv University, Technion

链接：https://arxiv.org/abs/2102.01646

【4】 OPAM: Online Purchasing-behavior Analysis using Machine learning

标题：OPAM：基于机器学习的在线购买行为分析

作者：Sohini Roychowdhury,Ebrahim Alareqi,Wenxi Li

机构：Director, ML Curriculum, Data Scientist, Product Labs Graduate Student Researcher, Data-X Lab, FourthBrain.ai, CA-, USA, Volvo Cars Technology, CA, University of California, Berkeley

备注：8 pages, 8 figures, 5 tables

链接：https://arxiv.org/abs/2102.01625

【5】 Strongly Adaptive OCO with Memory

标题：带记忆的强自适应OCO

作者：Zhiyu Zhang,Ashok Cutkosky,Ioannis Ch. Paschalidis

机构：Boston University, yannispobu. edu

链接：https://arxiv.org/abs/2102.01623

【6】 Depth separation beyond radial functions

标题：径向函数以外的深度分离

作者：Luca Venturi,Samy Jelassi,Tristan Ozuch,Joan Bruna

机构：Courant Institute of Mathematical Sciences, New York University, New York, Princeton University, Princeton, Massachusetts Institute of Technology, Cambridge, Center for Data Science, New York University, New York

链接：https://arxiv.org/abs/2102.01621

【7】 Towards Multi-agent Reinforcement Learning for Wireless Network Protocol  Synthesis

标题：面向无线网络协议综合的多智能体强化学习

作者：Hrishikesh Dutta,Subir Biswas

机构：Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA

备注：Accepted and presented in 13th International Conference on COMmunication Systems & NETworkS (COMSNETS) 2021, Bangalore. Proceedings not published yet

链接：https://arxiv.org/abs/2102.01611

【8】 Symplectic Gaussian Process Dynamics

标题：辛高斯过程动力学

作者：Katharina Ensinger,Friedrich Solowjow,Michael Tiemann,Sebastian Trimpe

机构：Bosch Center for, Max Planck Institute, Institute for Data Science, Artificial Intelligence, for Intelligent Systems, Artificial Intelligence, in Mechanical Engineering, Stuttgart, Germany, Renningen, Germany RWTH Aachen University, Aachen, Germany

链接：https://arxiv.org/abs/2102.01606

【9】 FEDZIP: A Compression Framework for Communication-Efficient Federated  Learning

标题：FEDZIP：一种通信高效的联邦学习压缩框架

作者：Amirhossein Malekijoo,Mohammad Javad Fadaeieslam,Hanieh Malekijou,Morteza Homayounfar,Farshid Alizadeh-Shabdiz,Reza Rawassizadeh

机构：Semnan University, Semnan, Iran, The Iran University of Science and Technology, Amirkabir University of Technology, Tehran, Iran, Tehran,Iran, Reza rawassizadeh, Boston University, Boston, MA, USA, February

链接：https://arxiv.org/abs/2102.01593

【10】 The Min-Max Complexity of Distributed Stochastic Convex Optimization  with Intermittent Communication

标题：间歇通信分布式随机凸优化问题的最小-最大复杂度

作者：Blake Woodworth,Brian Bullins,Ohad Shamir,Nathan Srebro

机构：Toyota Technological Toyota Technological Weizmann Institute Toyota Technological, Institute at Chicago Institute at Chicago, of Science, weizmann. ac.il

备注：27 pages

链接：https://arxiv.org/abs/2102.01583

【11】 Size Matters

标题：大小很重要

作者：Mats L. Richter,Johan Byttner,Ulf Krumnack,Ludwdig Schallner,Justin Shenk

备注：Preprint

链接：https://arxiv.org/abs/2102.01582

【12】 Super-klust: Another Way of Piecewise Linear Classification

标题：SUPER-KUST：分段线性分类的另一种方法

作者：Rahman Salim Zengin,Volkan Sezer

机构：CAutonomous Mobility Group, Electrical and Electronics Engineering Faculty, Istanbul Technical University, Istanbul, Turkey

备注：5 pages, 10 figures, “for the source code, see this https URL”

链接：https://arxiv.org/abs/2102.01571

【13】 Symmetric Boolean Factor Analysis with Applications to InstaHide

标题：对称布尔因子分析及其在InstaHide中的应用

作者：Sitan Chen,Zhao Song,Runzhou Tao,Ruizhe Zhang

链接：https://arxiv.org/abs/2102.01570

【14】 A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous  Q-Learning and TD-Learning Variants

标题：异步Q-学习和TD-学习变体的有限样本保证的Lyapunov理论

作者：Zaiwei Chen,Siva Theja Maguluri,Sanjay Shakkottai,Karthikeyan Shanmugam

机构：Georgia Institute of Technology Georgia Institute of Technology, The University of Texas at Austin, IBM Research NY, sanjay. shakkottaiQutexas. edu Karthikeyan. Shanmugam,ibm. com

链接：https://arxiv.org/abs/2102.01567

【15】 Real-time detection of uncalibrated sensors using Neural Networks

标题：基于神经网络的未标定传感器实时检测

作者：Luis J. Muñoz-Molina,Ignacio Cazorla-Piñar,Juan P. Dominguez-Morales,Fernando Perez-Peña

机构：Robotics and Technology of Computers Lab., Universidad de Sevilla, Seville, Universidad de Cadiz, Spain.

链接：https://arxiv.org/abs/2102.01565

【16】 Guidance on the Assurance of Machine Learning in Autonomous Systems  (AMLAS)

标题：自主系统中机器学习保证指南(AMLAS)

作者：Richard Hawkins,Colin Paterson,Chiara Picardi,Yan Jia,Radu Calinescu,Ibrahim Habli

机构：Assuring Autonomy International Programme (AAIP), University of York, UK, Version , February

链接：https://arxiv.org/abs/2102.01564

【17】 Metrics and continuity in reinforcement learning

标题：强化学习中的度量和连续性

作者：Charline Le Lan,Marc G. Bellemare,Pablo Samuel Castro

机构：University of Oxford,Google Research, Brain Team

备注：Accepted at AAAI 2021

链接：https://arxiv.org/abs/2102.01514

【18】 Gaussian Experts Selection using Graphical Models

标题：基于图形模型的高斯专家选择

作者：Hamed Jalali,Martin Pawelczyk,Gjerji Kasneci

机构：University of Tuebingen, gjergji. kasneciQuni-tuebingen.de, February

链接：https://arxiv.org/abs/2102.01496

【19】 Drift Estimation with Graphical Models

标题：基于图解模型的漂移估计

作者：Luigi Riso,Marco Guerzoni

机构：University of Turin, DEMS, University of Milan-Bicocca, January

链接：https://arxiv.org/abs/2102.01458

【20】 Predicting the Time Until a Vehicle Changes the Lane Using LSTM-based  Recurrent Neural Networks

标题：基于LSTM的递归神经网络预测车辆变道时间

作者：Florian Wirthmüller,Marvin Klimke,Julian Schlechtriemen,Jochen Hipp,Manfred Reichert

备注：the article has been accepted for publication in IEEE Robotics and Automation Letters (RA-L), 8 pages, 5 figures, 6 tables

链接：https://arxiv.org/abs/2102.01431

【21】 Graph Classification Based on Skeleton and Component Features

标题：基于骨架和构件特征的图形分类

作者：Xue Liu,Wei Wei,Xiangnan Feng,Xiaobo Cao,Dan Sun

机构：a Beijing System Design Institute of Electro-Mechanic Engineering, Beijing, China, Beihang University, Beijing, China, Key Laboratory of Mathematics, Informatics and Behavioral Semantics Ministry of Education, China, Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University, Beijing, Peng Cheng Laboratory, Shenzhen, Guangdong, China

备注：25 pages, 7 figures, 2 tables

链接：https://arxiv.org/abs/2102.01428

【22】 AURSAD: Universal Robot Screwdriving Anomaly Detection Dataset

标题：AURSAD：通用机器人螺丝传动异常检测数据集

作者：Błażej Leporowski,Daniella Tola,Casper Hansen,Alexandros Iosifidis

机构：Aarhus University, Technicon ApS, February

链接：https://arxiv.org/abs/2102.01409

【23】 Unassisted Noise Reduction of Chemical Reaction Data Sets

标题：化学反应数据集的非辅助降噪

作者：Alessandra Toniato,Philippe Schwaller,Antonio Cardinale,Joppe Geluykens,Teodoro Laino

机构：IBM Research Europe-Zurich-, Rischlikon, Switzerland, University of Bern, Bern, Switzerland, University of Pisa, Pisa, Italy

链接：https://arxiv.org/abs/2102.01399

【24】 It’s always personal: Using Early Exits for Efficient On-Device CNN  Personalisation

标题：它总是个人化的：使用提前退出实现高效的设备上CNN个性化

作者：Ilias Leontiadis,Stefanos Laskaridis,Stylianos I. Venieris,Nicholas D. Lane

机构：Samsung AI Center, Cambridge University of Cambridge,  Indicates equal contribution., -Personalised Training

备注：Accepted at the 22nd International Workshop on Mobile Computing Systems and Applications (HotMobile), 2021

链接：https://arxiv.org/abs/2102.01393

【25】 Bayesian Neural Networks for Virtual Flow Metering: An Empirical Study

标题：贝叶斯神经网络用于虚拟流量计量的实证研究

作者：Bjarne Grimstad,Mathilde Hotvedt,Anders T. Sandnes,Odd Kolbjørnsen,Lars S. Imsland

机构：Kolbjornsen, Lars. Imsland, Trondheim, Norway, University of Oslo, Oslo, Norway

备注：29 pages, 8 figures

链接：https://arxiv.org/abs/2102.01391

【26】 AutoFreeze: Automatically Freezing Model Blocks to Accelerate  Fine-tuning

标题：自动冻结：自动冻结模型块以加快微调

作者：Yuhan Liu,Saurabh Agarwal,Shivaram Venkataraman

机构：University of Wisconsin-Madison

链接：https://arxiv.org/abs/2102.01386

【27】 Stability-Constrained Markov Decision Processes Using MPC

标题：基于MPC的稳定性约束马尔可夫决策过程

作者：Mario Zanon,Sébastien Gros,Michele Palladino

机构：a IMT School for Advanced Studies Lucca, Piazza San Francesco , Lucca, Italy, NTNU, Gloshaugen, Trondheim, Norway, Gran Sasso Science Institute-GSSI, via Michele Jacobucci , L’Aquila, Italy

链接：https://arxiv.org/abs/2102.01383

【28】 Federated Learning in Smart Cities: A Comprehensive Survey

标题：智慧城市中的联合学习：综述

作者：Zhaohua Zheng,Yize Zhou,Yilong Sun,Zhang Wang,Boyi Liu,Keqiu Li

机构：Tianjin Univeristy, China; ,Hainan Univeristy, China; ,University of Macau, ARTICLE HISTORY, Compiled February

链接：https://arxiv.org/abs/2102.01375

【29】 Leveraging IoT and Weather Conditions to Estimate the Riders Waiting for  the Bus Transit on Campus

标题：利用物联网和天气条件估计校园公交候车人数

作者：Ismail Arai,Ahmed Elnoshokaty,Samy El-Tawab

机构：Information Initiative Center, Computer Information Systems College of Integrated Science and Engineering, Nara Institute of Science and Technology Northern Michigan University, James Madison University, Nara, Japan, Michigan, USA, Virginia, USA

备注：6 pages, 10figures, PerIoT 2021

链接：https://arxiv.org/abs/2102.01364

【30】 Recent Advances in Adversarial Training for Adversarial Robustness

标题：对抗性健壮性训练的最新进展

作者：Tao Bai,Jinqi Luo,Jun Zhao,Bihan Wen

机构：Nanyang Technological University, Singapore

链接：https://arxiv.org/abs/2102.01356

【31】 Mining Feature Relationships in Data

标题：挖掘数据中的特征关系

作者：Andrew Lensen

机构：Victoria University of Wellington, PO Box , Wellington , New Zealand

备注：16 pages, accepted in EuroGP ’21

链接：https://arxiv.org/abs/2102.01355

【32】 Graph Coarsening with Neural Networks

标题：基于神经网络的图形粗化

作者：Chen Cai,Dingkang Wang,Yusu Wang

备注：International Conference on Learning Representations 2021

链接：https://arxiv.org/abs/2102.01350

【33】 Fast Exploration of Weight Sharing Opportunities for CNN Compression

标题：快速探索CNN压缩的权重分担机会

作者：Etienne Dupuis,David Novo,Ian O’Connor,Alberto Bosio

机构：Ecole Centrale de lyon, LIRMM, Universite de Montpellier, Institut des Nanotechnologies de lyon, and CNRS, Lyon, France, Montpellier, France

备注：Presented at DATE Friday Workshop on System-level Design Methods for Deep Learning on Heterogeneous Architectures (SLOHA 2021) (arXiv:2102.00818)

链接：https://arxiv.org/abs/2102.01345

【34】 Bit Error Tolerance Metrics for Binarized Neural Networks

标题：二值化神经网络的误码容限度量

作者：Sebastian Buschjäger,Jian-Jia Chen,Kuan-Hsun Chen,Mario Günzel,Katharina Morik,Rodion Novkin,Lukas Pfahler,Mikail Yayla

机构：These authors contributed equally, Technical University of Dortmund

备注：Presented at DATE Friday Workshop on System-level Design Methods for Deep Learning on Heterogeneous Architectures (SLOHA 2021) (arXiv:2102.00818)

链接：https://arxiv.org/abs/2102.01344

【35】 Benchmarking Quantized Neural Networks on FPGAs with FINN

标题：基于FINN的FPGA量化神经网络基准测试

作者：Quentin Ducasse,Pascal Cotret,Loïc Lagadec,Robert Stewart

机构：Lab-STICC, ENSTA Bretagne, Heriot-Watt University, Brest, France, Edinburgh, United Kingdom

备注：Presented at DATE Friday Workshop on System-level Design Methods for Deep Learning on Heterogeneous Architectures (SLOHA 2021) (arXiv:2102.00818)

链接：https://arxiv.org/abs/2102.01341

【36】 pseudo-Bayesian Neural Networks for detecting Out of Distribution Inputs

标题：伪贝叶斯神经网络在非分布输入检测中的应用

作者：Gagandeep Singh,Deepak Mishra

机构：Indian Institute of Technology, Jodhpur Indian Institute of Technology, Jodhpur, Rajasthan, India

链接：https://arxiv.org/abs/2102.01336

【37】 Anomaly Detection of Time Series with Smoothness-Inducing Sequential  Variational Auto-Encoder

标题：基于平滑度诱导的序贯变分自动编码器的时间序列异常检测

作者：Longyuan Li,Junchi Yan,Haiyang Wang,Yaohui Jin

备注：Accepted by IEEE Transactions on Neural Network and Learning System (TNNLS), 2020

链接：https://arxiv.org/abs/2102.01331

【38】 Reinforcement Learning with Probabilistic Boolean Network Models of  Smart Grid Devices

标题：基于概率布尔网络模型的智能电网设备强化学习

作者：Pedro J. Rivera Torres,Carlos Gershenson García,Samir Kanaan Izquierdo

机构： Centro de Ciencias de la Complejidad (C,), Universidad Nacional Autonoma de Mexico, Circuito Centro, Cultural SN, Cd. Universitaria, Delegacion Coyoacan, Ciudad de Mexico, Mexico.,  Bioinformatics and Biomedical Signals Laboratory, Centre de Recerca en Enginyeria Biomedica,Universitat, Politecnica de Catalunya, Facultat de Matematiques i Estadistica, Edifici U, CPau Gargallo, Barce-, lona, spain., Instituto de Investigaciones en Matematicas Aplicadas y en Sistemas, Universidad Nacional Autonoma de, Mexico, Ciudad de Mexico, Mexico.,  Lakeside Labs GmbH, Klagenfurt am, Wortherses, Austria.,  Institut de Recerca Sant Joan de Deu Esplugues de Llobregat, Barcelona, Spain

链接：https://arxiv.org/abs/2102.01297

【39】 Scaling Laws for Transfer

标题：传递的标度律

作者：Danny Hernandez,Jared Kaplan,Tom Henighan,Sam McCandlish

机构：OpenAI

备注：19 pages, 15 figures

链接：https://arxiv.org/abs/2102.01293

【40】 Predicting student performance using data from an auto-grading system

标题：使用来自自动评分系统的数据预测学生表现

作者：Huanyi Chen,Paul A. S. Ward

机构：Paul A.S. Ward, University of Waterloo, Waterloo, ON, Canada

链接：https://arxiv.org/abs/2102.01270

【41】 Evaluating the Interpretability of Generative Models by Interactive  Reconstruction

标题：基于交互重构的产生式模型可解释性评价

作者：Andrew Slavin Ross,Nina Chen,Elisa Zhao Hang,Elena L. Glassman,Finale Doshi-Velez

机构：Harvard University, Cambridge, MA, USA

备注：CHI 2021 accepted paper

链接：https://arxiv.org/abs/2102.01264

【42】 TinyML for Ubiquitous Edge AI

标题：面向泛在边缘人工智能的TinyML

作者：Stanislava Soro

机构：in this report are those of The MITRE, Corporation and should not be construed as an, official government position, policy, or, decision, unless designated by other, documentation., September , C, The MITRE Corporation.

链接：https://arxiv.org/abs/2102.01255

【43】 Fast Training of Provably Robust Neural Networks by SingleProp

标题：用SingleProp实现可证明鲁棒神经网络的快速训练

作者：Akhilan Boopathy,Tsui-Wei Weng,Sijia Liu,Pin-Yu Chen,Gaoyuan Zhang,Luca Daniel

机构： Massachusetts Institute of Technology,  MIT-IBM Watson AI Lab, IBM Research

备注：Published at AAAI 2021

链接：https://arxiv.org/abs/2102.01208

【44】 GraphDF: A Discrete Flow Model for Molecular Graph Generation

标题：GraphDF：一种用于分子图生成的离散流模型

作者：Youzhi Luo,Keqiang Yan,Shuiwang Ji

备注：14 pages, 4 figures

链接：https://arxiv.org/abs/2102.01189

【45】 Multi-modal Ensemble Models for Predicting Video Memorability

标题：预测视频记忆能力的多模态集成模型

作者：Tony Zhao,Irving Fang,Jeffrey Kim,Gerald Friedland

机构：University of California, Berkeley

链接：https://arxiv.org/abs/2102.01173

【46】 Reinforcement Learning for Decision-Making and Control in Power Systems:  Tutorial, Review, and Vision

标题：强化学习在电力系统决策与控制中的应用：教程、回顾与展望

作者：Xin Chen,Guannan Qu,Yujie Tang,Steven Low,Na Li

链接：https://arxiv.org/abs/2102.01168

【47】 System-reliability based multi-ensemble of GAN and one-class joint  Gaussian distributions for unsupervised real-time structural health  monitoring

标题：基于系统可靠性的GaN多集成和一类联合高斯分布无监督实时结构健康监测

作者：Mohammad Hesam Soleimani-Babakamali,Reza Sepasdar,Kourosh Nasrollahzadeh,Rodrigo Sarlo

机构：Virginia Tech University, Blacksburg, VA, USA, K. N. Toosi University of Technology, Tehran, Iran

链接：https://arxiv.org/abs/2102.01158

【48】 Real-time Prediction for Mechanical Ventilation in COVID-19 Patients  using A Multi-task Gaussian Process Multi-objective Self-attention Network

标题：基于多任务高斯过程多目标自关注网络的冠状病毒患者机械通气实时预测

作者：Kai Zhang,Siddharth Karanth,Bela Patel,Robert Murphy,Xiaoqian Jiang

机构：University of Texas Health Science Center at Houston, Houston, TX , USA, Houston, Houston, TX ,USA

备注：In review

链接：https://arxiv.org/abs/2102.01147

【49】 Comparing hundreds of machine learning classifiers and discrete choice  models in predicting travel behavior: an empirical benchmark

标题：比较数百种机器学习分类器和离散选择模型预测出行行为的经验基准

作者：Shenhao Wang,Baichuan Mo,Stephane Hess,Jinhua Zhao

机构：-Choice Modeling Centre Institute for Transport Studies, University of Leeds, – Media Lab, Massachusetts Institute of Technology, January

链接：https://arxiv.org/abs/2102.01130

【50】 SGD Generalizes Better Than GD (And Regularization Doesn’t Help)

标题：SGD比GD泛化得更好(而正则化无济于事)

作者：Idan Amir,Tomer Koren,Roi Livni

机构：February

链接：https://arxiv.org/abs/2102.01117

【51】 Exact Langevin Dynamics with Stochastic Gradients

标题：具有随机梯度的精确朗之万动力学

作者：Adrià Garriga-Alonso,Vincent Fortuin

机构：ETH Zurich, Switzerland

备注：13 pages, 2 figures. Accepted to the 3rd Symposium on Advances in Approximate Bayesian Inference (AABI 2021)

链接：https://arxiv.org/abs/2102.01691

【52】 Agent Incentives: A Causal Perspective

标题：代理人激励：一个因果视角

作者：Tom Everitt,Ryan Carey,Eric Langlois,Pedro A Ortega,Shane Legg

机构：I DeepMind,University of Oxford,University of Toronto,Vector Institute, Equal Contribution

备注：In Proceedings of the AAAI 2021 Conference. Supersedes arXiv:1902.09980, arXiv:2001.07118

链接：https://arxiv.org/abs/2102.01685

【53】 Learning domain-agnostic visual representation for computational  pathology using medically-irrelevant style transfer augmentation

标题：使用医学无关风格转移增强学习用于计算病理学的领域不可知的视觉表示

作者：Rikiya Yamashita,Jin Long,Snikitha Banda,Jeanne Shen,Daniel L. Rubin

机构：Stanford University

链接：https://arxiv.org/abs/2102.01678

【54】 The GEM Benchmark: Natural Language Generation, its Evaluation and  Metrics

标题：创业板基准：自然语言生成、评估和度量

作者：Sebastian Gehrmann,Tosin Adewumi,Karmanya Aggarwal,Pawan Sasanka Ammanamanchi,Aremu Anuoluwapo,Antoine Bosselut,Khyathi Raghavi Chandu,Miruna Clinciu,Dipanjan Das,Kaustubh D. Dhole,Wanyu Du,Esin Durmus,Ondřej Dušek,Chris Emezue,Varun Gangal,Cristina Garbacea,Tatsunori Hashimoto,Yufang Hou,Yacine Jernite,Harsh Jhamtani,Yangfeng Ji,Shailza Jolly,Dhruv Kumar,Faisal Ladhak,Aman Madaan,Mounica Maddela,Khyati Mahajan,Saad Mahamood,Bodhisattwa Prasad Majumder,Pedro Henrique Martins,Angelina McMillan-Major,Simon Mille,Emiel van Miltenburg,Moin Nadeem,Shashi Narayan,Vitaly Nikolaev,Rubungo Andre Niyongabo,Salomey Osei,Ankur Parikh,Laura Perez-Beltrachini,Niranjan Ramesh Rao,Vikas Raunak,Juan Diego Rodriguez,Sashank Santhanam,João Sedoc,Thibault Sellam,Samira Shaikh,Anastasia Shimorina,Marco Antonio Sobrevilla Cabezudo,Hendrik Strobelt,Nishant Subramani,Wei Xu,Diyi Yang,Akhila Yerukola,Jiawei Zhou

机构：Pedro Henrique Martin, Amelia&D, New York, Carnegie Mellon University, Charles University, Prague, Columbia University, ‘Cornell, University, ‘DFKI, Germany Edinburgh Centre for Robotics, Georgia Tech, Google Research, Harvard University,  Heriot-Watt University, Hugging Face,IBM Research,IT Delhi,JIT Hyderabad,Instituto de Telecomunicacoes, Intelligent Systems Lab, Intel, Johns-Hopkins University, Kwame Nkrumah University of Science and Technology, Lulea University of Technology, Masakhane Africa,Massachusetts Institute of Technology,Microsoft,National, Institute of Technology Karnataka India, New York University,Pompeu Fabra University,Samsung Research,Stanford, University, Technical University of Kaiserslautern,Technical University Munich, Tilburg University, trivago, Universite de Lorraine,University of North Carolina Charlotte,University of Edinburgh,University of Electronic, Science and Technology of China, University of California San Diego,University of Lagos,University of Michigan Ann

链接：https://arxiv.org/abs/2102.01672

【55】 Capacity and quantum geometry of parametrized quantum circuits

标题：参数化量子电路的容量和量子几何

作者：Tobias Haug,Kishor Bharti,M. S. Kim

机构：QOLS, Blackett Laboratory, Imperial College London SW,AZ, UK,  Centre for Quantum Technologies, National University of Singapore , Singapore

备注：10 pages, 9 figures. Code available at this https URL

链接：https://arxiv.org/abs/2102.01659

【56】 Heterogeneous Graph based Deep Learning for Biomedical Network Link  Prediction

标题：基于异构图的深度学习在生物医学网络链路预测中的应用

作者：Jinjiang Guo,Jie Li,Dawei Leng,Lurong Pan

机构：AIDD, Data Science, Global Health Drug Discovery Institute, Beijing, China

链接：https://arxiv.org/abs/2102.01649

【57】 A Novel Use of Discrete Wavelet Transform Features in the Prediction of  Epileptic Seizures from EEG Data

标题：离散小波变换特征在从脑电数据预测癫痫发作中的新应用

作者：Cyrille Feudjio,Victoire Djimna Noyum,Younous Perieukeu Mofendjou,Rockefeller,Ernest Fokoué

机构：Ernest Fokouec,, African Institute for Mathematical Sciences Crystal Gardens, Limbe Cameroon, Stellenbosch University, South Africa, Rochester Institute of Technology, Rochester, NY , ARTICLE INFO

链接：https://arxiv.org/abs/2102.01647

【58】 Generating images from caption and vice versa via CLIP-Guided Generative  Latent Space Search

标题：通过剪辑引导的生成性潜在空间搜索从字幕生成图像，反之亦然

作者：Federico A. Galatolo,Mario G. C. A. Cimino,Gigliola Vaglini

机构：University of Pisa, Pisa, Italy

链接：https://arxiv.org/abs/2102.01645

【59】 U-LanD: Uncertainty-Driven Video Landmark Detection

标题：U-LAND：不确定性驱动的视频地标检测

作者：Mohammad H. Jafari,Christina Luong,Michael Tsang,Ang Nan Gu,Nathan Van Woudenberg,Robert Rohling,Teresa Tsang,Purang Abolmaesumi

机构：joint detection of key frames and landmarks in videos. We, tackle a specifically challenging problem, where training, Lower, Higher, labels are noisy and highly sparse. U-LanD builds upon, a pivotal observation: a deep Bayesian landmark detector, Prediction Prediction Prediction, solely trained on key video frames has significantly lower, Confidence Confidence Confidence, in videos. We use this observation as an unsupervised, signal to automatically recognize key frames on which we, detect landmarks. As a test-bed for our framework, we use, ultrasound imaging videos of the heart, where sparse and, noisy clinical labels are only available for a single frame in, that U-LanD can exceedingly outperform the state-of-the-art, Non-key Frames Non-key, non-Bayesian counterpart by a noticeable absolute margin, of ,% in R, score, with almost no overhead imposed on the, .-, Time, model size. Our approach is generic and can be potentially, applied to other challenging data with noisy and sparse, Index Terms-Video landmark detection, uncertainty es-

链接：https://arxiv.org/abs/2102.01586

【60】 Approximately Solving Mean Field Games via Entropy-Regularized Deep  Reinforcement Learning

标题：熵正则深度强化学习近似求解平均场对策

作者：Kai Cui,Heinz Koeppl

机构：Technische Universitat Darmstadt, heinz. koepplObcs. tu-darmstadt.de

备注：Accepted to the 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021)

链接：https://arxiv.org/abs/2102.01585

【61】 Policy Analysis using Synthetic Controls in Continuous-Time

标题：基于连续时间综合控制的政策分析

作者：Alexis Bellot,Mihaela van der Schaar

机构：University of Cambridge,The Alan Turing Institute, University of California Los Angeles, February

链接：https://arxiv.org/abs/2102.01577

【62】 Medical Datasets Collections for Artificial Intelligence-based Medical  Image Analysis

标题：用于基于人工智能的医学图像分析的医学数据集集合

作者：Yang Wen

备注：6 pages, 1 table

链接：https://arxiv.org/abs/2102.01549

【63】 Predicting Propensity to Vote with Machine Learning

标题：用机器学习预测投票倾向

作者：Rebecca D. pollard,Sara M. Pollard,Scott Streit

备注：11 pages, 8 tables

链接：https://arxiv.org/abs/2102.01535

【64】 Transfer Learning in Magnetic Resonance Brain Imaging: a Systematic  Review

标题：转移学习在磁共振脑成像中的系统评价

作者：Juan Miguel Valverde,Vandad Imani,Ali Abdollahzadeh,Riccardo De Feo,Mithilesh Prakash,Robert Ciszek,Jussi Tohka

机构： A.I. Virtanen Institute for Molecular Sciences University of Eastern Finland, Kuopio, Finland;, t The order of these authors was randomized, Version February , submitted to J. Imaging

链接：https://arxiv.org/abs/2102.01530

【65】 Robust Attack Detection Approach for IIoT Using Ensemble Classifier

标题：基于集成分类器的IIoT鲁棒攻击检测方法

作者：V. Priya,I. Sumaiya Thaseen,Thippa Reddy Gadekallu,Mohamed K. Aboudaif,Emad Abouel Nasr

机构：Abouel Nasr, Vellore Institute of Technology, Vellore, India, Advanced Manufacturing Institute, King Saud University, Riyadh, Saudi Arabia, College of Engineering, King Saud University, Riyadh, Saudi Arabia, Received: , August ,; Accepted: , October

链接：https://arxiv.org/abs/2102.01515

【66】 ADePT: Auto-encoder based Differentially Private Text Transformation

标题：ADEPT：基于差分私文转换的自动编码器

作者：Satyapriya Krishna,Rahul Gupta,Christophe Dupuy

机构：Amazon Alexa

备注：None

链接：https://arxiv.org/abs/2102.01502

【67】 Analyzing dynamical disorder for charge transport in organic  semiconductors via machine learning

标题：用机器学习分析有机半导体中电荷输运的动力学无序

作者：Patrick Reiser,Manuel Konrad,Artem Fediai,Salvador Léon,Wolfgang Wenzel,Pascal Friederich

机构：Institute of Nanotechnology, Karlsruhe Institute of Technology(KIT), Hermann-von-Helmholtz-Platz , Eggenstein-Leopoldshafen, Germany, Institute of Theoretical Informatics, Karlsruhe Institute of Technology(KT),Am, Fasanengarten , Karlsruhe, Germany, Universidad Politecnica, de Madrid, C Jose Gutierrez Abascal, Madrid, Spain

链接：https://arxiv.org/abs/2102.01479

【68】 Individual dynamic prediction of clinical endpoint from large  dimensional longitudinal biomarker history: a landmark approach

标题：从高维纵向生物标记物历史中动态预测临床终点的个体：一种里程碑式的方法

作者：Anthony Devaux,Robin Genuer,Karine Pérès,Cécile Proust-Lima

机构：INSERM, BPH, U, University of Bordeaux, Bordeaux, France, INRIA Bordeaux Sud-Ouest, Talence, France, February

链接：https://arxiv.org/abs/2102.01466

【69】 Global Earth Magnetic Field Modeling and Forecasting with Spherical  Harmonics Decomposition

标题：基于球谐分解的全球地球磁场建模与预测

作者：Panagiotis Tigas,Téo Bloch,Vishal Upendran,Banafsheh Ferdoushi,Mark C. M. Cheung,Siddha Ganju,Ryan M. McGranaghan,Yarin Gal,Asti Bhatt

机构：To Bloch, OATML, University of Reading, IUCAA, University of Oxford, Reading, UK, Pune, India, Oxford, UK, University of New Hampshire, NVIDIA Corporation, Durham, NH, USA, Santa Clara, CA, USA, Oxford,UK, ASTRA LLC, Lockheed Martin, SRI International, Louisville, CO, USA, Advanced Technology Center Menlo Park, CA, USA, Palo Alto, CA, USA

备注：Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020), Vancouver, Canada

链接：https://arxiv.org/abs/2102.01447

【70】 Prediction of low-keV monochromatic images from polyenergetic CT scans  for improved automatic detection of pulmonary embolism

标题：预测来自多能量CT扫描的低keV单色图像以改进肺栓塞的自动检测

作者：Constantin Seibold,Matthias A. Fink,Charlotte Goos,Hans-Ulrich Kauczor,Heinz-Peter Schlemmer,Rainer Stiefelhagen,Jens Kleesiek

机构： Institute of Anthropomatics Robotics, Karlsruhe Institute of Technology, Germany, University Hospital Heidelberg, Germany,  German Cancer Research Center, Heidelberg, Germany, Institute for Al in Medicine(IKIM), University Hospital Essen, Germany

备注：4 pages, ISBI 2021

链接：https://arxiv.org/abs/2102.01445

【71】 An Abstraction-based Method to Verify Multi-Agent Deep  Reinforcement-Learning Behaviours

标题：一种基于抽象的多Agent深度强化学习行为验证方法

作者：Pierre El Mqirmi,Francesco Belardinelli,Borja G. León

机构：Borja G. Leon, Imperial College London, UK

备注：Extended version of AAMAS publication under the same name

链接：https://arxiv.org/abs/2102.01434

【72】 Robust data-driven discovery of partial differential equations with  time-dependent coefficients

标题：具有时变系数的偏微分方程的鲁棒数据驱动发现

作者：Aoxue Chen,Guang Lin

机构：Article submitted to journal, The University of Chicago, Chicago, IL , USA, Subject Areas:, Purdue University,West, Applied mathematics, Computational, Lafayette, IN , physics, Computer modelling and, Engineering, Purdue University, West Lafayette, IN, simulation

链接：https://arxiv.org/abs/2102.01432

【73】 Clustering with Penalty for Joint Occurrence of Objects: Computational  Aspects

标题：对象联合出现的带惩罚的聚类：计算方面

作者：Ondřej Sokol,Vladimír Holý

链接：https://arxiv.org/abs/2102.01424

【74】 aura-net : robust segmentation of phase-contrast microscopy images with  few annotations

标题：AURA-Net：少标注相位衬度显微镜图像的鲁棒分割

作者：Ethan Cohen,Virginie Uhlmann

机构： European Bioinformatics Institute, European Molecular Biology Laboratory, Cambridge,UK, Ecole Normale Superieure Paris-Saclay, Paris, France

备注：Accepted at ISBI 2021

链接：https://arxiv.org/abs/2102.01389

【75】 Internal Language Model Training for Domain-Adaptive End-to-End Speech  Recognition

标题：领域自适应端到端语音识别的内部语言模型训练

作者：Zhong Meng,Naoyuki Kanda,Yashesh Gaur,Sarangarajan Parthasarathy,Eric Sun,Liang Lu,Xie Chen,Jinyu Li,Yifan Gong

机构：Microsoft Corporation, Redmond, WA, USA

备注：5 pages, ICASSP 2021

链接：https://arxiv.org/abs/2102.01380

【76】 Enabling energy efficient machine learning on a Ultra-Low-Power vision  sensor for IoT

标题：在物联网超低功耗视觉传感器上实现高能效机器学习

作者：Francesco Paissan,Massimo Gottardi,Elisabetta Farella

机构：E,DA- ICT-irst,IRIS-CMM, Fondazione Bruno Kessler, Trento, Italy

备注：Presented at DATE Friday Workshop on System-level Design Methods for Deep Learning on Heterogeneous Architectures (SLOHA 2021) (arXiv:2102.00818)

链接：https://arxiv.org/abs/2102.01340

【77】 Multimodal Attention Fusion for Target Speaker Extraction

标题：用于目标说话人提取的多模态注意融合

作者：Hiroshi Sato,Tsubasa Ochiai,Keisuke Kinoshita,Marc Delcroix,Tomohiro Nakatani,Shoko Araki

机构：NTT Corporation, Japan

备注：7 pages, 5 figures

链接：https://arxiv.org/abs/2102.01326

【78】 A Graph-Constrained Changepoint Learning Approach for Automatic  QRS-Complex Detection

标题：一种基于图约束的QRS波群自动检测变点学习方法

作者：Atiyeh Fotoohinasab,Toby Hocking,Fatemeh Afghah

备注：accepted in Asilomar 2020 conference

链接：https://arxiv.org/abs/2102.01319

【79】 When Noise meets Chaos: Stochastic Resonance in Neurochaos Learning

标题：当噪声与混沌相遇：神经混沌学习中的随机共振

作者：Harikrishnan NB,Nithin Nagaraj

机构：Consciousness Studies Programme, National Institute of Advanced Studies, Indian Institute of Science Campus, Bengaluru, India., harikrishnannbOnias.res.in, nithinOnias.res.in, February

备注：12 pages, 19 figures, 1 Table

链接：https://arxiv.org/abs/2102.01316

【80】 Optimal Sequential Detection of Signals with Unknown Appearance and  Disappearance Points in Time

标题：具有未知出现点和消失点的信号的最优序贯检测

作者：Alexander G. Tartakovsky,Nikita R. Berenkov,Alexei E. Kolessa,Igor V. Nikiforov

链接：https://arxiv.org/abs/2102.01310

【81】 Human-Machine Collaborative Video Coding Through Cuboidal Partitioning

标题：基于立方体划分的人机协同视频编码

作者：Ashek Ahmmed,Manoranjan Paul,Manzur Murshed,David Taubman

机构：Charles Sturt University, Australia., Engineering, and Information Technology, Federation University, Australia., University of New South Wales, Australia.

链接：https://arxiv.org/abs/2102.01307

【82】 Stability and Generalization of the Decentralized Stochastic Gradient  Descent

标题：分散随机梯度下降的稳定性与推广

作者：Tao Sun,Dongsheng Li,Bao Wang

机构：College of Computer, National University of Defense Technology, Changsha, Hunan, China., Scientific Computing Imaging Institute, University of Utah, USA.

备注：None

链接：https://arxiv.org/abs/2102.01302

【83】 A Stochastic Time Series Model for Predicting Financial Trends using NLP

标题：基于NLP的金融趋势预测的随机时间序列模型

作者：Pratyush Muthukumar,Jie Zhong

机构：University of California, Irvine, California State University, Los Angeles, February

备注：16 pages, 7 figures

链接：https://arxiv.org/abs/2102.01290

【84】 Detection of Racial Bias from Physiological Responses

标题：从生理反应中检测种族偏见

作者：Fateme Nikseresht,Runze Yan,Rachel Lew,Yingzheng Liu,Rose M. Sebastian,Afsaneh Doryab

机构：University of Virginia, USA

备注：8 pages, 2 figures, 1 table

链接：https://arxiv.org/abs/2102.01287

【85】 Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion  Classification

标题：用于皮肤病变分类的不平衡小数据集上的单模型深度学习

作者：Peng Yao,Shuwei Shen,Mengjuan Xu,Peng Liu,Fan Zhang,Jinyu Xing,Pengfei Shao,Benjamin Kaffenberger,Ronald X. Xu

机构：Kaffenberger, and Ronald. Xu

链接：https://arxiv.org/abs/2102.01284

【86】 Local Differential Privacy Is Equivalent to Contraction of  $E_γ$-Divergence

标题：局部微分隐私等价于$E_γ$-散度的收缩

作者：Shahab Asoodeh,Maryam Aliakbarpour,Flavio P. Calmon

机构：Harvard University, University of Massachusetts Amherst

链接：https://arxiv.org/abs/2102.01258

【87】 PSLA: Improving Audio Event Classification with Pretraining, Sampling,  Labeling, and Aggregation

标题：PSLA：通过预训练、采样、标记和聚合改进音频事件分类

作者：Yuan Gong,Yu-An Chung,James Glass

链接：https://arxiv.org/abs/2102.01243

【88】 Time Adaptive Gaussian Model

标题：时间自适应高斯模型

作者：Federico Cieca,Veronica Tozzo

机构：Robotics, Informatics and System Engineering, Universita degli Studi di Genova, Massachusetts General, Hospital, Harvard Medical School,  These authors equally contributed to this paper.

备注：15 pages, 1 figures, supplementary material for conference submission

链接：https://arxiv.org/abs/2102.01238

【89】 Doubly Robust Thompson Sampling for linear payoffs

标题：线性收益的双稳健Thompson抽样

作者：Wonyoung Kim,Gi-soo Kim,Myunghee Cho Paik

机构：Seoul National University, Seoul, Republic of Korea

备注：18pages including Supplementary Materials

链接：https://arxiv.org/abs/2102.01229

【90】 Inducing Meaningful Units from Character Sequences with Slot Attention

标题：利用时隙注意从字符序列中归纳出有意义的单元

作者：Melika Behjati,James Henderson

机构：Idiap Research InstituteEPFL

链接：https://arxiv.org/abs/2102.01223

【91】 The Gene Mover’s Distance: Single-cell similarity via Optimal Transport

标题：基因移动者的距离：通过最优运输实现单细胞相似性

作者：Riccardo Bellazzi,Andrea Codegoni,Stefano Gualandi,Giovanna Nicora,Eleonora Vercesi

备注：16 pages, 8 figures

链接：https://arxiv.org/abs/2102.01218

【92】 Causal Inference with the Instrumental Variable Approach and Bayesian  Nonparametric Machine Learning

标题：基于工具变量方法和贝叶斯非参数机器学习的因果推理

作者：Robert E. McCulloch,Rodney A. Sparapani,Brent R. Logan,Purushottam W. Laud

备注：33 pages, 7 figures

链接：https://arxiv.org/abs/2102.01199

【93】 A Statistician Teaches Deep Learning

标题：一位统计学家教授深度学习

作者：G. Jogesh Babu,David Banks,Hyunsoon Cho,David Han,Hailin Sang,Shouyi Wang

备注：19 pages. accepted by Journal of Statistical Theory and Practice

链接：https://arxiv.org/abs/2102.01194

【94】 Reconstruction and Segmentation of Parallel MR Data using Image Domain  DEEP-SLR

标题：基于图像域Deper-SLR的并行MR数据重建与分割

作者：Aniket Pramanik,Mathews Jacob

机构：The University of Iowa, Iowa City, USA

链接：https://arxiv.org/abs/2102.01172

【95】 Visual Framing of Science Conspiracy Videos: Integrating Machine  Learning with Communication Theories to Study the Use of Color and Brightness

标题：科学阴谋视频的视觉组帧：将机器学习与传播学理论相结合研究颜色和亮度的使用

作者：Kaiping Chen,Sang Jung Kim,Sebastian Raschka,Qiantong Gao

机构：University of Wisconsin-Madison, Version: February ,st

链接：https://arxiv.org/abs/2102.01163

【96】 Improving Distantly-Supervised Relation Extraction through BERT-based  Label & Instance Embeddings

标题：基于ERT的标签和实例嵌入改进远程监督关系抽取

作者：Despina Christou,Grigorios Tsoumakas

机构：Aristotle University of Thessaloniki, Aristotle University of Thessaloniki,  Greece, christoudacsd. auth. gr

备注：10 pages, 4 figures

链接：https://arxiv.org/abs/2102.01156

【97】 Deep Music Information Dynamics

标题：深度音乐信息动力学

作者：Shlomo Dubnov

机构：University of California San Diego

备注：None

链接：https://arxiv.org/abs/2102.01133

【98】 Diagnosis of Acute Poisoning Using Explainable Artificial Intelligence

标题：基于可解释人工智能的急性中毒诊断

作者：Michael Chary,Ed W Boyer,Michele M Burns

机构： Weill Cornell Medical Centre, NY, NY,  Brigham and Women’s Hospital, Boston, Massachusetts,  Boston Children’s Hospital, Boston, Massachusetts

备注：Parts submitted to HICSS 54

链接：https://arxiv.org/abs/2102.01116

【99】 Machine-Learned Phase Diagrams of Generalized Kitaev Honeycomb Magnets

标题：广义Kitaev蜂窝磁体的机器学习相图

作者：Nihal Rao,Ke Liu,Marc Machaczek,Lode Pollet

机构： Arnold Sommerfeld Center for Theoretical Physics, University of Munich, Theresienstr , Minchen, Germany, Munich Center for Quantum Science and Technology (MCQST), Schellingstr. , Munchen, Germany,  Wilczek Quantum Center, Shanghai Jiao Tong University, Shanghai , China, (Dated: February ,)

备注：11 pages, 12 figures, 1 table

链接：https://arxiv.org/abs/2102.01103

【100】 MalNet: A Large-Scale Cybersecurity Image Database of Malicious Software

标题：MARNET：一个大规模的恶意软件网络安全图像库

作者：Scott Freitas,Rahul Duggal,Duen Horng Chau

链接：https://arxiv.org/abs/2102.01072

机器翻译，仅供参考