Symmetrization approach to concentration inequalities for empirical processes
| dc.creator | Panchenko, Dmitry | |
| dc.date | 2004-05-18 | |
| dc.date.accessioned | 2026-07-07T05:08:23Z | |
| dc.date.available | 2026-07-07T05:08:23Z | |
| dc.description | 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 {-1,+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. | |
| dc.description | 15 pages | |
| dc.identifier | https://arxiv.org/abs/math/0405354 | |
| dc.identifier | http://arxiv.org/abs/math/0405354 | |
| dc.identifier | 2003 Ann. Probab. 31 No.4 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/71236 | |
| dc.subject | Probability | |
| dc.subject | 62G05 | |
| dc.title | Symmetrization approach to concentration inequalities for empirical processes | |
| dc.type | text |