English

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.

Keywords

Cite

@article{arxiv.math/0410280,
  title  = {Improved Vapnik Cervonenkis bounds},
  author = {Olivier Catoni},
  journal= {arXiv preprint arXiv:math/0410280},
  year   = {2007}
}