Concentration inequalities using the entropy method
Boucheron, Stéphane ; Lugosi, Gábor ; Massart, Pascal
Ann. Probab., Tome 31 (2003) no. 1, p. 1583-1614 / Harvested from Project Euclid
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.
Publié le : 2003-07-14
Classification:  Concentration inequalities,  empirical processes,  random graphs.,  60E15,  60C05,  28A35,  05C80
@article{1055425791,
     author = {Boucheron, St\'ephane and Lugosi, G\'abor and Massart, Pascal},
     title = {Concentration inequalities using the entropy method},
     journal = {Ann. Probab.},
     volume = {31},
     number = {1},
     year = {2003},
     pages = { 1583-1614},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1055425791}
}
Boucheron, Stéphane; Lugosi, Gábor; Massart, Pascal. Concentration inequalities using the entropy method. Ann. Probab., Tome 31 (2003) no. 1, pp.  1583-1614. http://gdmltest.u-ga.fr/item/1055425791/