Risk bounds for statistical learning
摘要
We propose a general theorem providing upper bounds for the risk of an empirical risk minimizer (ERM).We essentially focus on the binary classification framework. We extend Tsybakov's analysis of the risk of an ERM under margin type conditions by using concentration inequalities for conveniently weighted empirical processes. This allows us to deal with ways of measuring the ``size'' of a class of classifiers other than entropy with bracketing as in Tsybakov's work. In particular, we derive new risk bounds for the ERM when the classification rules belong to some VC-class under margin conditions and discuss the optimality of these bounds in a minimax sense.
引用
@article{arxiv.math/0702683,
title = {Risk bounds for statistical learning},
author = {Pascal Massart and Élodie Nédélec},
journal= {arXiv preprint arXiv:math/0702683},
year = {2016}
}
备注
Published at http://dx.doi.org/10.1214/009053606000000786 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)