CiteULike mdreid's CiteULike Search Register Log in
CiteULike is a free online bibliography manager. Register and you can start organising your references online.

Local Rademacher complexities Export

by: Peter L. Bartlett, Olivier Bousquet, Shahar Mendelson
Annals of Statistics, Vol. 33, No. 4. (2005), pp. 1497-1537.

Citation Format

[Posts]

View FullText article


mdreid's tags for this article

bounds complexity data_dependent error inequality

X Reviews [Write a review of this article]

X Find related articles from these CiteULike users

X Find related articles with these CiteULike tags

X Posting History

X Abstract

We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empirical version of Rademacher averages, in the sense that the Rademacher averages are computed from the data, on a subset of functions with small empirical error. We present some applications to classification and prediction with convex function classes, and with kernel classes in particular.


X BibTeX record

X RIS record


Privacy Statement | Terms & Conditions
CiteULike organises scholarly (or academic) papers or literature and provides bibliographic (which means it makes bibliographies) for universities and higher education establishments. It helps undergraduates and postgraduates. People studying for PhDs or in postdoctoral (postdoc) positions. The service is similar in scope to EndNote or RefWorks or any other reference manager like BibTeX, but it is a social bookmarking service for scientists and humanities researchers.