QUT ePrints

Local Rademacher complexities

Bartlett, Peter L., Bousquet, Olivier , & Mendelson, Shahar (2005) Local Rademacher complexities. The Annals of Statistics, 33(4), pp. 1497-1537.

View at publisher

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.

Impact and interest:

90 citations in Scopus
Search Google Scholar™
68 citations in Web of Science®

Citation countsare sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

ID Code: 43986
Item Type: Journal Article
Additional URLs:
Keywords: Error bounds, concentration inequalities, data-dependent complexity, Rademacher averages
DOI: 10.1214/009053605000000282
ISSN: 0090-5364
Subjects: Australian and New Zealand Standard Research Classification > MATHEMATICAL SCIENCES (010000) > STATISTICS (010400)
Australian and New Zealand Standard Research Classification > ECONOMICS (140000) > ECONOMETRICS (140300)
Divisions: Past > QUT Faculties & Divisions > Faculty of Science and Technology
Past > Schools > Mathematical Sciences
Copyright Owner: Copyright 2005 Institute of Mathematical Statistics
Deposited On: 18 Aug 2011 08:52
Last Modified: 01 Mar 2012 00:34

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page