A new concentration result for regularized risk minimizers

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We establish a new concentration result for regularized risk minimizers which is similar to an oracle inequality. Applying this inequality to regularized least squares minimizers like least squares support vector machines, we show that these algorithms learn with (almost) the optimal rate in some specific situations. In addition, for regression our results suggest that using the loss function $L_α(y,t)=|y-t|^α$ with $α$ near 1 may often be preferable to the usual choice of $α=2$.
Published at http://dx.doi.org/10.1214/074921706000000897 in the IMS Lecture Notes Monograph Series (http://www.imstat.org/publications/lecnotes.htm) by the Institute of Mathematical Statistics (http://www.imstat.org)

Keywords

Statistics Theory

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/131287

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/math/0612779
 http://arxiv.org/abs/math/0612779
 IMS Lecture Notes Monograph Series 2006, Vol. 51, 260-275
 doi:10.1214/074921706000000897

Collections

arXiv