SIA OpenIR  > 机器人学研究室
On Convergence Properties of Implicit Self-paced Objective
Ma, Zilu1; Liu, Shiqi1; Meng DY(孟德宇)1,2; Zhang, Yong3; Lo, SioLong4; Han Z(韩志)2
Department机器人学研究室
Source PublicationInformation Sciences
ISSN0020-0255
2018
Volume462Pages:132-140
Indexed BySCI ; EI
EI Accession number20182505321508
WOS IDWOS:000443666300008
Contribution Rank2
Funding OrganizationNational Key R&D Program of China ; China NSFC
KeywordSelf-paced Learning Machine Learning Non-convex Optimization Convergence
Abstract

Self-paced learning (SPL) is a new methodology that simulates the learning principle of humans/animals to start learning easier aspects of a learning task, and then gradually take more complex examples into training. This new-coming learning regime has been empirically substantiated to be effective in various computer vision and pattern recognition tasks. Recently, it has been proved that the SPL regime has a close relationship with a implicit self-paced objective function. While this implicit objective could provide helpful interpretations to the effectiveness, especially the robustness, insights under the SPL paradigms, there are still no theoretical results to verify such relationship. To this issue, we provide some convergence results on the implicit objective of SPL. Specifically, we will prove that the learning process of SPL always converges to critical points of this implicit objective under some mild conditions. This result verifies the intrinsic relationship between SPL and this implicit objective, and makes the previous robustness analysis on SPL complete and theoretically rational.

Language英语
WOS SubjectComputer Science, Information Systems
WOS Research AreaComputer Science
Funding ProjectNational Key R&D Program of China[SQ2018YFB100000] ; China NSFC[61661166011] ; China NSFC[11690011] ; China NSFC[61603292] ; China NSFC[61721002]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/22104
Collection机器人学研究室
Corresponding AuthorMeng DY(孟德宇)
Affiliation1.School of Mathematics and Statistics and Ministry of Education Key Lab of Intelligent Networks and Network Security, Xian Jiaotong University, China;
2.State key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China;
3.First Affiliated Hospital of Xi'an Jiaotong University, Xian Jiaotong University, China;
4.Faculty of Information Technology, Macau University of Science and Technology, China
Recommended Citation
GB/T 7714
Ma, Zilu,Liu, Shiqi,Meng DY,et al. On Convergence Properties of Implicit Self-paced Objective[J]. Information Sciences,2018,462:132-140.
APA Ma, Zilu,Liu, Shiqi,Meng DY,Zhang, Yong,Lo, SioLong,&Han Z.(2018).On Convergence Properties of Implicit Self-paced Objective.Information Sciences,462,132-140.
MLA Ma, Zilu,et al."On Convergence Properties of Implicit Self-paced Objective".Information Sciences 462(2018):132-140.
Files in This Item: Download All
File Name/Size DocType Version Access License
On Convergence Prope(398KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ma, Zilu]'s Articles
[Liu, Shiqi]'s Articles
[Meng DY(孟德宇)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ma, Zilu]'s Articles
[Liu, Shiqi]'s Articles
[Meng DY(孟德宇)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ma, Zilu]'s Articles
[Liu, Shiqi]'s Articles
[Meng DY(孟德宇)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: On Convergence Properties of Implicit Self-paced Objective.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.