PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

On concentration of self-bounding functions
Stephane Boucheron, Gábor Lugosi and Pascal Massart
Electronic Journal of Statistics Volume 14, pp. 1884-1899, 2009.

Abstract

We prove some new concentration inequalities for self-bounding functions using the entropy method. As an application, we recover Talagrand’s convex distance inequality. The new Bernstein-like inequalities for self-bounding functions are derived thanks to a careful analysis of the so-called Herbst argument. The latter involves comparison results between solutions of differential inequalities that may be interesting in their own right.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Theory & Algorithms
ID Code:6639
Deposited By:Gábor Lugosi
Deposited On:08 March 2010