Concentration inequalities using the entropy method
Stéphane Boucheron, Gábor Lugosi, Pascal Massart · The Annals of Probability · 2003
We investigate a new methodology, worked out by Ledoux and Massart, to prove concentration-of-measure inequalities. The method is based on certain modified logarithmic Sobolev inequalities. We provide some very simple and general ready-to-use inequalities. One of these inequalities may be considered as an exponential version of the Efron--Stein inequality. The main purpose of this paper is to point out the simplicity and the generality of the approach. We show how the new method can recover many of Talagrand's revolutionary inequalities and provide new applications in a variety of problems including Rademacher averages, Rademacher chaos, the number of certain small subgraphs in a random graph, and the minimum of the empirical risk in some statistical estimation problems.
Cited by 235 works. doi:10.1214/aop/1055425791
Authors
References
- Weak Convergence and Empirical Processes
- On the method of bounded differences
- The Concentration of Measure Phenomenon
- Probability in Banach Spaces
- On general minimax theorems
- Random Graphs
- The Jackknife Estimate of Variance
- Probability in Banach Spaces
- Random Graphs
- Empirical Margin Distributions and Bounding the Generalization Error of Combined Classifiers