Improved Vapnik Cervonenkis bounds
Statistics Theory
2007-06-13 v1 Probability
Statistics Theory
Abstract
We give a new proof of VC bounds where we avoid the use of symmetrization and use a shadow sample of arbitrary size. We also improve on the variance term. This results in better constants, as shown on numerical examples. Moreover our bounds still hold for non identically distributed independent random variables. Keywords: Statistical learning theory, PAC-Bayesian theorems, VC dimension.
Cite
@article{arxiv.math/0410280,
title = {Improved Vapnik Cervonenkis bounds},
author = {Olivier Catoni},
journal= {arXiv preprint arXiv:math/0410280},
year = {2007}
}