Rademacher processes and bounding the risk of function learning

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We construct data dependent bounds on the risk in function learning problems. The bounds are based on the local norms of the Rademacher process indexed by the underlying function class and they do not require prior knowledge about the distribution of the training examples or any specific properties of the function class.
14 pages

Keywords

Probability, 60G35

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/71228

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/math/0405338
 http://arxiv.org/abs/math/0405338
 2000 In: High Dimensional Probability II pp. 443 - 459

Collections

arXiv