Learning Rates for l1-Regularized Kernel Classifiers
Joint Authors
Yang, Fenghong
Chen, Di-Rong
Tong, Hongzhi
Source
Journal of Applied Mathematics
Issue
Vol. 2013, Issue 2013 (31 Dec. 2013), pp.1-11, 11 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2013-11-17
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Abstract EN
We consider a family of classification algorithms generated from a regularization kernel scheme associated with l1-regularizer and convex loss function.
Our main purpose is to provide an explicit convergence rate for the excess misclassification error of the produced classifiers.
The error decomposition includes approximation error, hypothesis error, and sample error.
We apply some novel techniques to estimate the hypothesis error and sample error.
Learning rates are eventually derived under some assumptions on the kernel, the input space, the marginal distribution, and the approximation error.
American Psychological Association (APA)
Tong, Hongzhi& Chen, Di-Rong& Yang, Fenghong. 2013. Learning Rates for l1-Regularized Kernel Classifiers. Journal of Applied Mathematics،Vol. 2013, no. 2013, pp.1-11.
https://search.emarefa.net/detail/BIM-476299
Modern Language Association (MLA)
Tong, Hongzhi…[et al.]. Learning Rates for l1-Regularized Kernel Classifiers. Journal of Applied Mathematics No. 2013 (2013), pp.1-11.
https://search.emarefa.net/detail/BIM-476299
American Medical Association (AMA)
Tong, Hongzhi& Chen, Di-Rong& Yang, Fenghong. Learning Rates for l1-Regularized Kernel Classifiers. Journal of Applied Mathematics. 2013. Vol. 2013, no. 2013, pp.1-11.
https://search.emarefa.net/detail/BIM-476299
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-476299