Paper #280

Title:

An inequality for uniform deviations of sample averages from their means

Authors:

Peter Bartlett and Gábor Lugosi

Date:

February 1998

Abstract:

We derive a new inequality for uniform deviations of averages from their means. The inequality is a common generalization of previous results of Vapnik and Chervonenkis (1974) and Pollard (1986). Using the new inequality we obtain tight bounds for empirical loss minimization learning.

Keywords:

Vapnik-Chervonenkis inequality, uniform laws of large numbers, empirical risk, minimization

JEL codes:

C13

Area of Research:

Statistics, Econometrics and Quantitative Methods

Published in:

Statistics and Probability Letters, 44, (1999), pp. 55-62

Download the paper in PDF format