2019 53rd Asilomar Conference on Signals, Systems, and Computers最新文献_第7页

Imaging with Distributed Lensless Line Sensors 分布式无透镜线传感器成像

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/IEEECONF44664.2019.9048751

Yucheng Zheng, M. Salman Asif

引用次数: 1

On the Role of Sampling in Underdetermined Tensor Decomposition with Kronecker and Khatri-Rao Structured Factors 基于Kronecker和Khatri-Rao结构因子的欠定张量分解中抽样的作用

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/IEEECONF44664.2019.9048911

Mehmet Can Hücümenoğlu, P. Pal

引用次数: 0

Empirical and Simulated Performance Evaluation of Distributed Massive MIMO 分布式大规模MIMO的经验与仿真性能评价

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/IEEECONF44664.2019.9049062

David Löschenbrand, M. Hofer, B. Rainer, T. Zemen

引用次数: 5

Manifold Proximal Point Algorithms for Dual Principal Component Pursuit and Orthogonal Dictionary Learning 对偶主成分追踪与正交字典学习的流形近点算法

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/IEEECONF44664.2019.9048840

Shixiang Chen, Zengde Deng, Shiqian Ma, A. M. So

引用次数: 22

Generalization, Adaptation and Low-Rank Representation in Neural Networks 神经网络的泛化、自适应与低秩表示

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/IEEECONF44664.2019.9048845

Samet Oymak, Zalan Fabian, Mingchen Li, M. Soltanolkotabi

{"title":"Generalization, Adaptation and Low-Rank Representation in Neural Networks","authors":"Samet Oymak, Zalan Fabian, Mingchen Li, M. Soltanolkotabi","doi":"10.1109/IEEECONF44664.2019.9048845","DOIUrl":"https://doi.org/10.1109/IEEECONF44664.2019.9048845","url":null,"abstract":"We develop a data-dependent optimization and generalization theory for neural networks which leverages the lowrankness of the Jacobian matrix associated with the network. Our results help demystify why training and generalization is easier on clean and structured datasets and harder on noisy and unstructured datasets. Specifically, we show that over the principal eigendirections of the Jacobian matrix space learning is fast and one can quickly train a model with zero training loss that can also generalize well. Over the smaller eigendirections, training is slower and early stopping can help with generalization at the expense of some bias. We also discuss how neural networks can learn better representations over time in terms of the Jacobian mapping. We conduct various numerical experiments on deep networks that corroborate our theoretical findings and demonstrate that: (i) the Jacobian of typical neural networks exhibit low-rank structure with a few large singular values and many small ones, (ii) most of the useful label information lies on the principal eigendirections where learning is fast, and (iii) Jacobian adapts over time and learn better representations.","PeriodicalId":6684,"journal":{"name":"2019 53rd Asilomar Conference on Signals, Systems, and Computers","volume":"9 1","pages":"581-585"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80109109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

The Fifty-Third Asilomar Conference on Signals, Systems & Computers [Title pae i] 第53届Asilomar信号、系统与计算机会议[标题页1]

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/ieeeconf44664.2019.9048851

引用次数: 0

Control and data channel combining in Ultra-Reliable Low-Latency Communication 超可靠低延迟通信中的控制和数据通道组合

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/IEEECONF44664.2019.9048795

Trung-Kien Le, U. Salim, F. Kaltenberger

引用次数: 2

Decentralized Massive MIMO Uplink Signal Estimation by Binary Multistep Synthesis 基于二值多步合成的分散海量MIMO上行信号估计

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/IEEECONF44664.2019.9048772

Pascal Seidel, S. Paul, Jochen Rust

引用次数: 3

Lp Quasi-norm Minimization Lp拟范数最小化

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/IEEECONF44664.2019.9048923

M. Ashour, C. Lagoa, N. S. Aybat

引用次数: 4

IEEECONF 2019 Foreword

2019 53rd Asilomar Conference on Signals, Systems, and Computers Pub Date : 2019-11-01 DOI: 10.1109/ieeeconf44664.2019.9048880

引用次数: 0