机器学习每日论文速递[03.15]

访问arxivdaily.com，获取带摘要的学术速递，更多学科、收藏、评论、搜索……应有尽有。同步公众号(arXiv每日学术速递)，欢迎关注

cs.LG 方向，今日共计65篇

【1】 Multiview Sensing With Unknown Permutations: An Optimal Transport Approach
标题：具有未知排列的多视角传感：一种最优传输方法
作者：Yanting Ma,Petros T. Boufounos,Hassan Mansour,Shuchin Aeron
备注：5 pages, 3 figures, ICASSP 2021
链接：https://arxiv.org/abs/2103.07458

【2】 EventGraD: Event-Triggered Communication in Parallel Machine Learning
标题：EventGraD：并行机器学习中的事件触发通信
作者：Soumyadip Ghosh,Bernardo Aquino,Vijay Gupta
机构*：University of Notre Dame, USA
备注：Preprint submitted
链接：https://arxiv.org/abs/2103.07454

【3】 Efficient reconstruction of depth three circuits with top fan-in two
标题：采用顶部扇入二次的深度三回路的高效重建
作者：Gaurav Sinha
备注：41 pages
链接：https://arxiv.org/abs/2103.07445

【4】 A Neural Network for Semigroups
标题：半群的一种神经网络
作者：Edouard Balzin,Boris Shminke
备注：12 pages, 2 figures, 5 tables
链接：https://arxiv.org/abs/2103.07388

【5】 Game-theoretic Understanding of Adversarially Learned Features
标题：对抗性学习特征的博弈论理解
作者：Jie Ren,Die Zhang,Yisen Wang,Lu Chen,Zhanpeng Zhou,Xu Cheng,Xin Wang,Yiting Chen,Jie Shi,Quanshi Zhang
链接：https://arxiv.org/abs/2103.07364

【6】 Self-Feature Regularization: Self-Feature Distillation Without Teacher Models
标题：自我特征正规化：没有教师模型的自我特征提炼
作者：Wenxuan Fan,Zhenyan Hou
机构*：Science& Engineering (DUT-RUISE), Science& Engineering(dut-RUISE-), Dalian University of Technology, Dalian, China, March
链接：https://arxiv.org/abs/2103.07350

【7】 Second-Order Component Analysis for Fault Detection
标题：二阶分量分析在故障检测中的应用
作者：Peng Jingchao,Zhao Haitao,Hu Zhengwei
链接：https://arxiv.org/abs/2103.07303

【8】 Automating the GDPR Compliance Assessment for Cross-border Personal Data Transfers in Android Applications
标题：自动化Android应用程序中跨境个人数据传输的GDPR合规性评估
作者：Danny S. Guamán,Xavier Ferrer,Jose M. del Alamo,Jose Such
备注：Author's copy of the submitted manuscript
链接：https://arxiv.org/abs/2103.07297

【9】 Adversarial Graph Disentanglement
标题：对抗性图解缠
作者：Shuai Zheng,Zhenfeng Zhu,Zhizhe Liu,Shuiwang Ji,Yao Zhao
机构*：IInstitute of Information Science, Beijing Jiaotong University, Beijing, China, Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China, Texas&M University, College Station, TX
备注：In process
链接：https://arxiv.org/abs/2103.07295

【10】 VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts
标题：VDSM：基于状态空间建模和专家深度混合的无监督视频解缠
作者：Matthew J. Vowels,Necati Cihan Camgoz,Richard Bowden
机构*：Richard bowden, m.j. vowelssurrey.ac.uk, Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK
链接：https://arxiv.org/abs/2103.07292

【11】 Neural Networks with Complex-Valued Weights Have No Spurious Local Minima
标题：具有复数权值的神经网络无伪局部极小
作者：Xingtu Liu
机构*：March
链接：https://arxiv.org/abs/2103.07287

【12】 Integration of Convolutional Neural Networks in Mobile Applications
标题：卷积神经网络在移动应用中的集成
作者：Roger Creus Castanyer,Silverio Martínez-Fernández,Xavier Franch
机构*：Silverio Martinez-Fernandez, Universitat Politecnica de Catalunya Universitat Politecnica de catalunya Universitat Politecnica de Catalunya, Barcelona, spain, Barcelona,Spain
备注：Pre-print. Accepted and to be published in WAIN@ICSE 2021
链接：https://arxiv.org/abs/2103.07286

【13】 Patient-specific virtual spine straightening and vertebra inpainting: An automatic framework for osteoplasty planning
标题：特定于患者的虚拟脊柱矫直和椎体修复：一种用于成骨计划的自动框架
作者：Christina Bukas,Bailiang Jian,Luis F. Rodriguez Venegas,Francesca De Benetti,Sebastian Ruehling,Anjany Sekubojina,Jens Gempt,Jan S. Kirschke,Marie Piraud,Johannes Oberreuter,Nassir Navab,Thomas Wendler
备注：7 pages, 5 figures, 5 tables
链接：https://arxiv.org/abs/2103.07279

【14】 Modelling Animal Biodiversity Using Acoustic Monitoring and Deep Learning
标题：基于声学监测和深度学习的动物生物多样性建模
作者：C. Chalmers,P. Fergus,S. Wich,S. N. Longmore
链接：https://arxiv.org/abs/2103.07276

【15】 Adversarial Machine Learning Security Problems for 6G: mmWave Beam Prediction Use-Case
标题：6G对抗性机器学习安全问题：毫米波波束预测用例
作者：Evren Catak,Ferhat Ozgur Catak,Arild Moldsvor
机构*：Norwegian University of, Simula research Lab., Science and Technology, Fornebu, Norway, Gjovik, Norway
备注：7 pages
链接：https://arxiv.org/abs/2103.07268

【16】 Robust and generalizable embryo selection based on artificial intelligence and time-lapse image sequences
标题：基于人工智能和延时图像序列的鲁棒可推广胚胎选择
作者：Jørgen Berntsen,Jens Rimestad,Jacob Theilgaard Lassen,Dang Tran,Mikkel Fly Kragh
链接：https://arxiv.org/abs/2103.07262

【17】 Knowledge- and Data-driven Services for Energy Systems using Graph Neural Networks
标题：利用图神经网络为能源系统提供知识和数据驱动的服务
作者：Francesco Fusco,Bradley Eck,Robert Gormally,Mark Purcell,Seshu Tirupathi
机构*：IBM Research Europe, Dublin, Ireland
备注：Accepted for publication in proceedings of IEEE Conference of Big Data 2020
链接：https://arxiv.org/abs/2103.07248

【18】 Projection-based QLP Algorithm for Efficiently Computing Low-Rank Approximation of Matrices
标题：高效计算矩阵低秩逼近的基于投影的QLP算法
作者：Maboud F. Kaloorazi,Jie Chen
链接：https://arxiv.org/abs/2103.07245

【19】 BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks
标题：BDD4BNN：一种基于BDD的二值化神经网络定量分析框架
作者：Yedi Zhang,Zhe Zhao,Guangke Chen,Fu Song,Taolue Chen
机构*：ShanghaiTech University, Shanghai, China, University of Surrey, Surrey, UK
链接：https://arxiv.org/abs/2103.07224

【20】 Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation
标题：领域好奇心：学习有效的领域适应数据收集策略
作者：Karol Arndt,Oliver Struckmeier,Ville Kyrki
链接：https://arxiv.org/abs/2103.07223

【21】 Real-time Timbre Transfer and Sound Synthesis using DDSP
标题：基于DDSP的实时音色传输和声音合成
作者：Francesco Ganis,Erik Frej Knudesn,Søren V. K. Lyster,Robin Otterbein,David Südholt,Cumhur Erkut
机构*：Design, and Media Technology, Aalborg University Copenhagen, Denmark
链接：https://arxiv.org/abs/2103.07220

【22】 In the light of feature distributions: moment matching for Neural Style Transfer
标题：基于特征分布的矩匹配法在神经风格转换中的应用
作者：Nikolai Kalischek,Jan Dirk Wegner,Konrad Schindler
机构*：Jan D. Wegner, Eco Vision Lab, Photogrammetry and Remote Sensing, ETH Zurich, P. Picasso, W. Kandinsky, V. Van Gogh, G. Richter, C. Monet
链接：https://arxiv.org/abs/2103.07208

【23】 Medical data wrangling with sequential variational autoencoders
标题：使用顺序变分自动编码器的医疗数据争论
作者：Daniel Barrejón,Pablo M. Olmos,Antonio Artés-Rodríguez
链接：https://arxiv.org/abs/2103.07206

【24】 Latent Space Explorations of Singing Voice Synthesis using DDSP
标题：基于DDSP的歌声合成的潜在空间探索
作者：Juan Alonso,Cumhur Erkut
机构*：Design, and Media Technology, Aalborg University Copenhagen, Denmark
链接：https://arxiv.org/abs/2103.07197

【25】 Process Comparison Using Object-Centric Process Cubes
标题：使用以对象为中心的进程多维数据集进行进程比较
作者：Anahita Farhang Ghahfarokhi,Alessandro Berti,Wil M. P. van der Aalst
链接：https://arxiv.org/abs/2103.07184

【26】 Visualising Deep Network's Time-Series Representations
标题：深度网络时间序列表示的可视化
作者：Błażej Leporowski,Alexandros Iosifidis
机构*：Aarhus University, Denmark
链接：https://arxiv.org/abs/2103.07176

【27】 Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability
标题：伯特是一个跨学科的知识学习者吗？关于预训练模型可移植性的一个令人惊讶的发现
作者：Wei-Tsung Kao,Hung-Yi Lee
机构*：National Taiwan University
备注：9 pages, 7 figures
链接：https://arxiv.org/abs/2103.07162

【28】 Learnable Companding Quantization for Accurate Low-bit Neural Networks
标题：精确低位神经网络的可学习压扩量化
作者：Kohei Yamamoto
机构*：Oki Electric Industry Co., Ltd.
备注：Accepted at CVPR 2021
链接：https://arxiv.org/abs/2103.07156

【29】 Auction Based Clustered Federated Learning in Mobile Edge Computing System
标题：移动边缘计算系统中基于拍卖的分簇联邦学习
作者：Renhao Lu,Weizhe Zhang,Qiong Li,Xiaoxiong Zhong,Athanasios V. Vasilakos
链接：https://arxiv.org/abs/2103.07150

【30】 Learning spectro-temporal representations of complex sounds with parameterized neural networks
标题：用参数化神经网络学习复杂声音的时域表示
作者：Rachid Riad,Julien Karadayi,Anne-Catherine Bachoud-Lévi,Emmanuel Dupoux
机构*：Dupoux, Ecole des Hautes Etudes en Sciences Sociales, Centre National de la Recherche, Scientifique, INRIA, Ecole Normale Superieure-Pe- Sciences Lettres University, rue d'ulm, Paris, France, NeuroPsychologie Interventionnelle, Departement d'Etudes Cognitives, Ecole Normale Superieure, Institut national de la sante et de la recherche medicale, Institut Mondor de Recherche Biomedicale Neuratris, Universite Paris-Est Creteil, Paris Sciences Lettres University, rue d'ulm, Paris, Facebook AI Research, Paris, France, (Dotod. , Morah ,)
链接：https://arxiv.org/abs/2103.07125

【31】 GA for feature selection of EEG heterogeneous data
标题：基于遗传算法的脑电异质数据特征选择
作者：Aurora Saibene,Francesca Gasparini
机构*：s and Communications, Multi Media Signal Processing Laboratory Viale Sarca , Milan, Italy, University of Milano-Bicocca, NeuroMI, Piazza dell'Ateneo Nuovo , Milan, Italy
备注：submitted to Expert Systems with Applications
链接：https://arxiv.org/abs/2103.07117

【32】 Training Networks in Null Space of Covariance for Continual Learning
标题：用于持续学习的协方差零空间中的训练网络
作者：Shipeng Wang,Xiaorong Li,Jian Sun,Zongben Xu
机构*：Xi'an Jiaotong University, Xi'an, China, National Engineering Laboratory of Big Data Algorithms and Analysis Technology, Xi'an, China, Pazhou Lab, Guangzhou, Guangdong, China
链接：https://arxiv.org/abs/2103.07113

【33】 On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models
标题：基于机器学习模型的属性推理攻击可行性研究
作者：Benjamin Zi Hao Zhao,Aviral Agrawal,Catisha Coburn,Hassan Jameel Asghar,Raghav Bhaskar,Mohamed Ali Kaafar,Darren Webb,Peter Dickinson
机构*：Macquarie University, University of New South Wales, +Data,-CSIRO, SBITS Pilani K. K. Birla Goa campus, Cyber Electronic Warfare Division, Defence Science and Technology Group, australia
备注：20 pages, accepted at IEEE EuroS&P 2021
链接：https://arxiv.org/abs/2103.07101

【34】 DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks
标题：动态网络中预测任务的DynACPD嵌入算法
作者：Chris Connell,Yang Wang
备注：35 pages
链接：https://arxiv.org/abs/2103.07080

【35】 Can Single-Shuffle SGD be Better than Reshuffling SGD and GD?
标题：单一洗牌SGD能比重新洗牌SGD和GD更好吗？
作者：Chulhee Yun,Suvrit Sra,Ali Jadbabaie
机构*：jadbabaiOmit. edu, Massachusetts Institute of Technology, Cambridge, MA, USA
备注：26 pages, 2 figures
链接：https://arxiv.org/abs/2103.07079

【36】 Improving Authorship Verification using Linguistic Divergence
标题：利用语言发散度改进作者身份验证
作者：Yifan Zhang,Dainis Boumber,Marjan Hosseinia,Fan Yang,Arjun Mukherjee
机构*：University of Houston
备注：Published in ROMCIR 2021. Workshop held as part of ECIR 2021. March 28 - April 1, 2021
链接：https://arxiv.org/abs/2103.07052

【37】 SCEI: A Smart-Contract Driven Edge Intelligence Framework for IoT Systems
标题：SCEI：一种智能契约驱动的物联网边缘智能框架
作者：Chenhao Xu,Yong Li,Yao Deng,Jiaqi Ge,Longxiang Gao,Mengshi Zhang,Yong Xiang,Xi Zheng
备注：12 pages, 9 figures
链接：https://arxiv.org/abs/2103.07050

【38】 Bilingual Dictionary-based Language Model Pretraining for Neural Machine Translation
标题：基于双语词典的神经机器翻译语言模型预训练
作者：Yusen Lin,Jiayong Lin,Shuaicheng Zhang,Haoying Dai
机构*：Univ. of Maryland Univ. of Maryland Univ. of Maryland Univ. of Maryland
链接：https://arxiv.org/abs/2103.07040

【39】 Interleaving Learning, with Application to Neural Architecture Search
标题：交织学习及其在神经结构搜索中的应用
作者：Hao Ban,Pengtao Xie
机构*：PIXIEQENG. UCSD. EDU, University of California San Diego
备注：arXiv admin note: substantial text overlap with arXiv:2012.04863
链接：https://arxiv.org/abs/2103.07018

【40】 On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions
标题：关于观测预报时态图与静电图表示的等价性
作者：Jianfei Gao,Bruno Ribeiro
机构*： Purdue University, West Lafayette, In, U.S.A.
链接：https://arxiv.org/abs/2103.07016

【41】 Large Batch Simulation for Deep Reinforcement Learning
标题：深度强化学习的大批量仿真
作者：Brennan Shacklett,Erik Wijmans,Aleksei Petrenko,Manolis Savva,Dhruv Batra,Vladlen Koltun,Kayvon Fatahalian
机构*： Stanford University , Georgia Institute of Technology ,Intel Labs, University of Southern California ,Simon Fraser University
备注：Published as a conference paper at ICLR 2021
链接：https://arxiv.org/abs/2103.07013

【42】 Learning by Teaching, with Application to Neural Architecture Search
标题：教中学及其在神经结构搜索中的应用
作者：Parth Sheth,Yueyu Jiang,Pengtao Xie
机构*：PARTHFOURQGMAIL.COM, Y,JIANGQENG. UCSD. EDU, University of California San Diego
链接：https://arxiv.org/abs/2103.07009

【43】 Federated Functional Gradient Boosting
标题：联合泛函梯度助推
作者：Zebang Shen,Hamed Hassani,Satyen Kale,Amin Karbasi
机构*：University of Pennsylvania, Google Research, Yale
链接：https://arxiv.org/abs/2103.06972

【44】 Adversarial attacks in consensus-based multi-agent reinforcement learning
标题：基于共识的多智能体强化学习中的对抗性攻击
作者：Martin Figura,Krishna Chaitanya Kosaraju,Vijay Gupta
链接：https://arxiv.org/abs/2103.06967

【45】 Efficient Pairwise Neuroimage Analysis using the Soft Jaccard Index and 3D Keypoint Sets
标题：基于软Jaccard指数和三维关键点集的高效成对神经图像分析
作者：Laurent Chauvin,Kuldeep Kumar,Christian Desrosiers,William Wells III,Matthew Toews
备注：10 pages, 7 figures
链接：https://arxiv.org/abs/2103.06966

【46】 A Reinforcement Learning Based Approach to Play Calling in Football
标题：一种基于强化学习的足球传球方法
作者：Preston Biro,Stephen G. Walker
机构*：March
备注：62 pages, 25 figures
链接：https://arxiv.org/abs/2103.06939

【47】 The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop
标题：FGVC7研讨会上的半监督iNaturist-Aves挑战赛
作者：Jong-Chyi Su,Subhransu Maji
机构*：University of Massachusetts Amherst
备注：Tech report for Semi-iNat 2020 challenge, please see this http URL
链接：https://arxiv.org/abs/2103.06937

【48】 Stochastic-HMDs: Adversarial Resilient Hardware Malware Detectors through Voltage Over-scaling
标题：随机HMD：通过电压过缩放的对抗性弹性硬件恶意软件检测器
作者：Md Shohidul Islam,Ihsen Alouani,Khaled N. Khasawneh
机构*：ECE Dept., George Mason University, Fairfax, VA, USA, CSE Dept., Dhaka University of Engineering& Technology, Gazipur Bangladesh, IEMN CNRS-UMR, Universite Polytechniqu Hauts-De-France, Valenciennes, France
备注：13 pages, 13 figures
链接：https://arxiv.org/abs/2103.06936

【49】 Linnaeus: A highly reusable and adaptable ML based log classification pipeline
标题：Linnaeus：一种高度可重用、适应性强的基于ML的日志分类流水线
作者：Armin Catovic,Carolyn Cartwright,Yasmin Tesfaldet Gebreyesus,Simone Ferlin
机构*：Ericsson AB, Stockholm, Sweden
备注：8 pages, 7 figures; to be included in ICSE/WAIN'21
链接：https://arxiv.org/abs/2103.06927

【50】 Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models
标题：NLU模型快捷学习行为的解释与缓解
作者：Mengnan Du,Varun Manjunatha,Rajiv Jain,Ruchi Deshpande,Franck Dernoncourt,Jiuxiang Gu,Tong Sun,Xia Hu
机构*：ITexas A&M University, Adobe Research
备注：Accepted by NAACL 2021
链接：https://arxiv.org/abs/2103.06922

【51】 On Improving Deep Learning Trace Analysis with System Call Arguments
标题：用系统调用参数改进深度学习跟踪分析
作者：Quentin Fournier,Daniel Aloise,Seyed Vahid Azhari,François Tetreault
机构*：Polytechnique montreal, Polytechnique Montreal, Ciena, Quebec H,T ,J, Ottawa K,K OL
备注：11 pages, 11 figures, IEEE/ACM MSR 2021
链接：https://arxiv.org/abs/2103.06915

【52】 Modern Dimension Reduction
标题：现代降维
作者：Philip D. Waggoner
机构*：University of Chicago, pdwaggonerOuchicago. edu, Forthcoming, Cambridge University Presso
备注：83 pages, 36 figures, to appear in the Cambridge University Press Elements in Quantitative and Computational Methods for the Social Sciences series
链接：https://arxiv.org/abs/2103.06885

【53】 Machine Learning Assisted Orthonormal Basis Selection for Functional Data Analysis
标题：函数数据分析中的机器学习辅助正交基选择
作者：Rani Basna,Hiba Nassar,Krzysztof Podgórski
链接：https://arxiv.org/abs/2103.07453

【54】 Radiomic Deformation and Textural Heterogeneity (R-DepTH) Descriptor to characterize Tumor Field Effect: Application to Survival Prediction in Glioblastoma
标题：放射形变和纹理异质性(R-深度)描述符表征瘤野效应：在胶质母细胞瘤生存预测中的应用
作者：Marwa Ismail,Prateek Prasanna,Kaustav Bera,Volodymyr Statsevych,Virginia Hill,Gagandeep Singh,Sasan Partovi,Niha Beig,Sean McGarry,Peter Laviolette,Manmeet Ahluwalia,Anant Madabhushi,Pallavi Tiwari
链接：https://arxiv.org/abs/2103.07423

【55】 Optimal sequential decision making with probabilistic digital twins
标题：概率数字孪生最优序贯决策
作者：Christian Agrell,Kristina Rognlien Dahl,Andreas Hafver
机构*：Group Research and Development, DNV, Norway, University of Oslo, Norway
备注：23 pages, 5 figures
链接：https://arxiv.org/abs/2103.07405

【56】 Empirical Mode Modeling: A data-driven approach to recover and forecast nonlinear dynamics from noisy data
标题：经验模态建模：一种从噪声数据中恢复和预测非线性动力学的数据驱动方法
作者：Joseph Park,Gerald M Pao,Erik Stabenau,George Sugihara,Thomas Lorimer
机构*：Lorimer, Received: date
备注：Submitted to Nonlinear Dynamics
链接：https://arxiv.org/abs/2103.07281

【57】 Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition
标题：基于BPE-Dropout的低资源端到端语音识别动态声学单元增强
作者：Aleksandr Laptev,Andrei Andrusenko,Ivan Podluzhny,Anton Mitrofanov,Ivan Medennikov,Yuri Matveev
机构*：Corporate Laboratory of Human-Machine Interaction Technologies, Information Technologies and Programming Faculty, ITMO University, Saint-Petersburg, Russia , STC-innovations Ltd, Saint-Petersburg, Russia
备注：16 pages, 7 figures
链接：https://arxiv.org/abs/2103.07186

【58】 Explainable AI by BAPC -- Before and After correction Parameter Comparison
标题：用BAPC解释的人工智能--校正前后的参数比较
作者：Florian Sobieczky,Salma Mahmoud,Simon Neugebauer,Lukas Rippitsch,Manuela Geiß
机构*：GeiB, Software Competence Center Hagenberg GmbH, Hagenberg, Austria, Speedinvest Heroes Consulting GmbH, Vienna, Austria
链接：https://arxiv.org/abs/2103.07155

【59】 Discovering Diverse Solutions in Deep Reinforcement Learning
标题：深度强化学习中不同解的发现
作者：Takayuki Osa,Voot Tangkaratt,Masashi Sugiyama
机构*：Kyushu Institute of Technology, Fukuoka, Japan, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan, University of Tokyo, Tokyo, Japan
备注：18 pages
链接：https://arxiv.org/abs/2103.07084

【60】 Evidence-Based Policy Learning
标题：基于证据的政策学习
作者：Jann Spiess,Vasilis Syrgkanis
链接：https://arxiv.org/abs/2103.07066

【61】 Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer
标题：视觉变换器在CXR上冠状病毒严重程度定量和病变定位中的应用
作者：Gwanghyun Kim,Sangjoon Park,Yujin Oh,Joon Beom Seo,Sang Min Lee,Jin Hwan Kim,Sungjun Moon,Jae-Kwang Lim,Jong Chul Ye
机构*： Korea Advanced Institute of Science and Technology, Daejeon, South Korea, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea, College of Medicine, Chungnam National Univerity, Daejeon, South Korea, College of Medicine, Yeungnam University, Daegu, South Korea, Kyungpook National University, Daegu, South Korea
备注：8 pages
链接：https://arxiv.org/abs/2103.07062

【62】 Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus
标题：基于胸部X线特征库的视觉转换器在冠状病毒CXR诊断中的应用
作者：Sangjoon Park,Gwanghyun Kim,Yujin Oh,Joon Beom Seo,Sang Min Lee,Jin Hwan Kim,Sungjun Moon,Jae-Kwang Lim,Jong Chul Ye
机构*：Jong Chul Y,-,-, Korea Advanced Institute of Science and Technology, Daejeon, South Korea, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea, College of Medicine, Chungnam National Univerity, Daejeon, South Korea, College of Medicine, Yeungnam University, Daegu, South Korea, Kyungpook National University, Daegu, South Korea
备注：10 pages
链接：https://arxiv.org/abs/2103.07055

【63】 Max-Linear Regression by Scalable and Guaranteed Convex Programming
标题：可伸缩保凸规划的极大线性回归
作者：Seonho Kim,Sohail Bahmani,Kiryung Lee
机构*：KIM. ,QOSU.EDU, The Ohio State University, Columbus, OH , SOHAIL. BAHMANIQECE. GATECH. EDU, Georgia Institute of Technology, Atlanta, GA , LEE. ,http://QOSU.EDU
链接：https://arxiv.org/abs/2103.07020

【64】 Physics and Computing Performance of the Exa.TrkX TrackML Pipeline
标题：Exa.TrkX TrackML流水线的物理和计算性能
作者：Xiangyang Ju,Daniel Murnane,Paolo Calafiura,Nicholas Choma,Sean Conlon,Steve Farrell,Yaoyuan Xu,Maria Spiropulu,Jean-Roch Vlimant,Adam Aurisano,Jeremy Hewes,Giuseppe Cerati,Lindsey Gray,Thomas Klijnsma,Jim Kowalkowski,Markus Atkinson,Mark Neubauer,Gage DeZoort,Savannah Thais,Aditi Chauhan,Alex Schuy,Shih-Chieh Hsu,Alex Ballow,and Alina Lazar
机构*：ILawrence Berkeley National Laboratory, Berkeley, CA, USA, California Institute of Technology, Pasadena, CA USA, University of Cincinnati, Cincinnati, OH USA, Fermi National Accelerator Laboratory, Batavia, IL USA, University of Illinois at Urbana-Champaign, Urbana, IL, USA, Princeton University, Princeton, NJ, USA, University of Washington, Seattle, WA, USA, Youngstown State University, Youngstown, OH, USA
链接：https://arxiv.org/abs/2103.06995

【65】 The Minecraft Kernel: Modelling correlated Gaussian Processes in the Fourier domain
标题：“我的世界”核心：傅里叶域中的相关高斯过程建模
作者：Fergus Simpson,Alexis Boukouvalas,Vaclav Cadek,Elvijs Sarkans,Nicolas Durrande
机构*：Secondmind
备注：None
链接：https://arxiv.org/abs/2103.06950

机器翻译，仅供参考；“机构”仅供参考