Symmetrization approach to concentration inequalities for empirical processes
Panchenko, Dmitry
Ann. Probab., Tome 31 (2003) no. 1, p. 2068-2081 / Harvested from Project Euclid
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.
Publié le : 2003-10-14
Classification:  Empirical processes,  concentration inequalities,  60E15,  60F10
@article{1068646378,
     author = {Panchenko, Dmitry},
     title = {Symmetrization approach to concentration inequalities for empirical processes},
     journal = {Ann. Probab.},
     volume = {31},
     number = {1},
     year = {2003},
     pages = { 2068-2081},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1068646378}
}
Panchenko, Dmitry. Symmetrization approach to concentration inequalities for empirical processes. Ann. Probab., Tome 31 (2003) no. 1, pp.  2068-2081. http://gdmltest.u-ga.fr/item/1068646378/