中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
Towards Better Generalization of Deep Neural Networks via Non-Typicality Sampling Scheme

文献类型：期刊论文

作者Peng, Xinyu3; Wang, Fei-Yue2; Li, Li1
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2022-02-11
页码11
关键词Training Estimation Deep learning Standards Optimization Noise measurement Convergence Deep learning generalization performance nontypicality sampling scheme stochastic gradient descent (SGD)
ISSN号2162-237X
DOI10.1109/TNNLS.2022.3147031
通讯作者Li, Li(li-li@tsinghua.edu.cn)
英文摘要Improving the generalization performance of deep neural networks (DNNs) trained by minibatch stochastic gradient descent (SGD) has raised lots of concerns from deep learning practitioners. The standard simple random sampling (SRS) scheme used in minibatch SGD treats all training samples equally in gradient estimation. In this article, we study a new data selection method based on the intrinsic property of the training set to help DNNs have better generalization performance. Our theoretical analysis suggests that this new sampling scheme, called the nontypicality sampling scheme, boosts the generalization performance of DNNs through biasing the solution toward wider minima, under certain assumptions. We confirm our findings experimentally and show that more variants of minibatch SGD can also benefit from the new sampling scheme. Finally, we discuss an extension of the nontypicality sampling scheme that holds promise to enhance both generalization performance and convergence speed of minibatch SGD.
资助项目National Key Research and Development Program of China[2020AAA0108104]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000757938800001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China
源URL[http://ir.ia.ac.cn/handle/173211/47888]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者Li, Li
作者单位1.Tsinghua Univ, Tsinghua Natl Lab Informat Sci & Technol, Dept Automat, Beijing 100084, Peoples R China
2.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100080, Peoples R China
3.Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China
推荐引用方式
GB/T 7714		 Peng, Xinyu,Wang, Fei-Yue,Li, Li. Towards Better Generalization of Deep Neural Networks via Non-Typicality Sampling Scheme[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:11.
APA Peng, Xinyu,Wang, Fei-Yue,&Li, Li.(2022).Towards Better Generalization of Deep Neural Networks via Non-Typicality Sampling Scheme.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,11.
MLA Peng, Xinyu,et al."Towards Better Generalization of Deep Neural Networks via Non-Typicality Sampling Scheme".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):11.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。