Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples
Joint Authors
Wu, Wei
Yao, Mingchen
Zhang, Chao
Source
Discrete Dynamics in Nature and Society
Issue
Vol. 2015, Issue 2015 (31 Dec. 2015), pp.1-8, 8 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2015-11-19
Country of Publication
Egypt
No. of Pages
8
Main Subjects
Abstract EN
Many generalization results in learning theory are established under the assumption that samples are independent and identically distributed (i.i.d.).
However, numerous learning tasks in practical applications involve the time-dependent data.
In this paper, we propose a theoretical framework to analyze the generalization performance of the empirical risk minimization (ERM) principle for sequences of time-dependent samples (TDS).
In particular, we first present the generalization bound of ERM principle for TDS.
By introducing some auxiliary quantities, we also give a further analysis of the generalization properties and the asymptotical behaviors of ERM principle for TDS.
American Psychological Association (APA)
Yao, Mingchen& Zhang, Chao& Wu, Wei. 2015. Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples. Discrete Dynamics in Nature and Society،Vol. 2015, no. 2015, pp.1-8.
https://search.emarefa.net/detail/BIM-1060779
Modern Language Association (MLA)
Yao, Mingchen…[et al.]. Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples. Discrete Dynamics in Nature and Society No. 2015 (2015), pp.1-8.
https://search.emarefa.net/detail/BIM-1060779
American Medical Association (AMA)
Yao, Mingchen& Zhang, Chao& Wu, Wei. Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples. Discrete Dynamics in Nature and Society. 2015. Vol. 2015, no. 2015, pp.1-8.
https://search.emarefa.net/detail/BIM-1060779
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1060779