Translator Disclaimer
October 2003 Symmetrization approach to concentration inequalities for empirical processes
Dmitry Panchenko
Ann. Probab. 31(4): 2068-2081 (October 2003). DOI: 10.1214/aop/1068646378

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 $\{0,1\}^n.$ 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.

Citation

Download Citation

Dmitry Panchenko. "Symmetrization approach to concentration inequalities for empirical processes." Ann. Probab. 31 (4) 2068 - 2081, October 2003. https://doi.org/10.1214/aop/1068646378

Information

Published: October 2003
First available in Project Euclid: 12 November 2003

zbMATH: 1042.60008
MathSciNet: MR2016612
Digital Object Identifier: 10.1214/aop/1068646378

Subjects:
Primary: 60E15
Secondary: 60F10

Rights: Copyright © 2003 Institute of Mathematical Statistics

JOURNAL ARTICLE
14 PAGES


SHARE
Vol.31 • No. 4 • October 2003
Back to Top