MetaCartSign in to MyCiteSeer

Include Citations | Advanced Search | Help

Include Citations | Advanced Search | Help

  Entropy numbers of linear function classes (2000) [5 citations — 2 self]

Download:
Download as a PDF | Download as a PS
by Robert C. Williamson, Alex J. Smola, Bernhard Sch Olkopf
In N. Cesa-Bianchi & S. Goldman (Eds.), Proceedings of the 13th Annual Conference on Computational Learning Theory
http://www.learningtheory.org/colt2000/papers/WilliamsonSmolaScholkopf.ps
Add To MetaCart

Abstract:

This paper collects together a miscellany of results originally motivated by the analysis of the generalization performance of the "maximum-margin " algorithm due to Vapnik and others. The key feature of the paper is its operator-theoretic viewpoint. New bounds on covering numbers for classes related to Maximum Margin classes are derived directly without making use of a combinatorial dimension such as the VC-dimension. Specific contents of the paper include: a new and self-contained proof of Maurey's theorem and some generalizations with small explicit values of constants; bounds on the covering numbers of maximum margin classes suitable for the analysis of their generalization performance; the extension of such classes to those induced by balls in quasi-Banach spaces (such as ` p-norms with 0 1). extension of results on the covering numbers of convex hulls of basis functions to p-convex hulls (0 1); an appendix containing the tightest known bounds on the entropy numbers of the identity operator between ` n

Citations

No citations identified.