Towards Better Generalization of Deep Neural Networks via Non-Typicality Sampling Scheme

doi:10.1109/TNNLS.2022.3147031

CORC > 自动化研究所 > 中国科学院自动化研究所 > 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

	Towards Better Generalization of Deep Neural Networks via Non-Typicality Sampling Scheme
	Peng, Xinyu 1; Wang, Fei-Yue 2; Li, Li 3
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	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
DOI	10.1109/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
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000757938800001
资助机构	National Key Research and Development Program of China
内容类型	期刊论文
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, 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, Tsinghua Natl Lab Informat Sci & Technol, 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.