Header logo is

Localized Rademacher Complexities

2002

Conference Paper

ei

We investigate the behaviour of global and local Rademacher averages. We present new error bounds which are based on the local averages and indicate how data-dependent local averages can be estimated without {it a priori} knowledge of the class at hand.

Author(s): Bartlett, P. and Bousquet, O. and Mendelson, S.
Journal: Proceedings of the 15th annual conference on Computational Learning Theory
Pages: 44-58
Year: 2002
Day: 0
Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)
Event Name: Proceedings of the 15th annual conference on Computational Learning Theory
Digital: 0
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik
Links: PDF
PostScript

BibTex 

@inproceedings{1442,
  title = {Localized Rademacher Complexities},
  author = {Bartlett, P. and Bousquet, O. and Mendelson, S.},
  journal = {Proceedings of the 15th annual conference on Computational Learning Theory},
  pages = {44-58},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  year = {2002}
}