Translator Disclaimer
June 2005 Square root penalty: Adaptation to the margin in classification and in edge estimation
A. B. Tsybakov, S. A. van de Geer
Ann. Statist. 33(3): 1203-1224 (June 2005). DOI: 10.1214/009053604000001066

Abstract

We consider the problem of adaptation to the margin in binary classification. We suggest a penalized empirical risk minimization classifier that adaptively attains, up to a logarithmic factor, fast optimal rates of convergence for the excess risk, that is, rates that can be faster than n−1/2, where n is the sample size. We show that our method also gives adaptive estimators for the problem of edge estimation.

Citation

Download Citation

A. B. Tsybakov. S. A. van de Geer. "Square root penalty: Adaptation to the margin in classification and in edge estimation." Ann. Statist. 33 (3) 1203 - 1224, June 2005. https://doi.org/10.1214/009053604000001066

Information

Published: June 2005
First available in Project Euclid: 1 July 2005

zbMATH: 1080.62047
MathSciNet: MR2195633
Digital Object Identifier: 10.1214/009053604000001066

Subjects:
Primary: 62G07
Secondary: 62G08, 62H30, 68T10

Rights: Copyright © 2005 Institute of Mathematical Statistics

JOURNAL ARTICLE
22 PAGES


SHARE
Vol.33 • No. 3 • June 2005
Back to Top