ALBERT — All Library Books, journals and Electronic Records Telegrafenberg

Hits per page

hit 1 - 1 | 1 hit

Select All Export

Unknown

Learning Rates for -Regularized Kernel Classifiers (2013)

Hongzhi Tong, Di-Rong Chen, and Fenghong Yang

Hindawi

In: Journal of Applied Mathematics

add to mindlist on the mindlist

Details

Publication Date: 2013-11-18

Description: We consider a family of classification algorithms generated from a regularization kernel scheme associated with -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.

Print ISSN: 1110-757X

Electronic ISSN: 1687-0042

Topics: Mathematics

Published by Hindawi

	Location	Call Number	Expected	Availability

Others were also interested in ...

PAPER CURRENT

S·F·X

Fulltext

hit 1 - 1 | 1 hit