Symmetrization approach to concentration inequalities for empirical processes
Probability
2007-05-23 v1
Abstract
We introduce a symmetrization technique that allows us to translate a problem of controlling the deviation of some functionals on a product space from their mean into a problem of controlling the deviation between two independent copies of the functional. As an application we give a new easy proof of Talagrand's concentration inequality for empirical processes, where besides symmetrization we use only Talagrand's concentration inequality on the discrete cube {-1,+1}^n. As another application of this technique we prove new Vapnik-Chervonenkis type inequalities. For example, for VC-classes of functions we prove a classical inequality of Vapnik and Chervonenkis only with normalization by the sum of variance and sample variance.
Cite
@article{arxiv.math/0405354,
title = {Symmetrization approach to concentration inequalities for empirical processes},
author = {Dmitry Panchenko},
journal= {arXiv preprint arXiv:math/0405354},
year = {2007}
}
Comments
15 pages