CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Developing Learning Algorithms via Optimized Discretization of Continuous Dynamical Systems
Tao, Qing1,2; Sun, Zhengya1; Kong, Kang2
Source PublicationIEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS
2012-02-01
Volume42Issue:1Pages:140-149
SubtypeArticle
AbstractMost of the existing numerical optimization methods are based upon a discretization of some ordinary differential equations. In order to solve some convex and smooth optimization problems coming from machine learning, in this paper, we develop efficient batch and online algorithms based on a new principle, i.e., the optimized discretization of continuous dynamical systems (ODCDSs). First, a batch learning projected gradient dynamical system with Lyapunov's stability and monotonic property is introduced, and its dynamical behavior guarantees the accuracy of discretization-based optimizer and applicability of line search strategy. Furthermore, under fair assumptions, a new online learning algorithm achieving regret O(root T) or O(logT) is obtained. By using the line search strategy, the proposed batch learning ODCDS exhibits insensitivity to the step sizes and faster decrease. With only a small number of line search steps, the proposed stochastic algorithm shows sufficient stability and approximate optimality. Experimental results demonstrate the correctness of our theoretical analysis and efficiency of our algorithms.
KeywordDynamical Systems Line Search Machine Learning Online Learning Optimization Algorithms Projected Subgradient Algorithms Regret
WOS HeadingsScience & Technology ; Technology
WOS KeywordNEURAL-NETWORK
Indexed BySCI
Language英语
WOS Research AreaAutomation & Control Systems ; Computer Science
WOS SubjectAutomation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS IDWOS:000302096700011
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/10743
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Affiliation1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.New Star Res Inst Appl Technol, Hefei 230031, Peoples R China
Recommended Citation
GB/T 7714
Tao, Qing,Sun, Zhengya,Kong, Kang. Developing Learning Algorithms via Optimized Discretization of Continuous Dynamical Systems[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS,2012,42(1):140-149.
APA Tao, Qing,Sun, Zhengya,&Kong, Kang.(2012).Developing Learning Algorithms via Optimized Discretization of Continuous Dynamical Systems.IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS,42(1),140-149.
MLA Tao, Qing,et al."Developing Learning Algorithms via Optimized Discretization of Continuous Dynamical Systems".IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 42.1(2012):140-149.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tao, Qing]'s Articles
[Sun, Zhengya]'s Articles
[Kong, Kang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tao, Qing]'s Articles
[Sun, Zhengya]'s Articles
[Kong, Kang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tao, Qing]'s Articles
[Sun, Zhengya]'s Articles
[Kong, Kang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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