×

Some local measures of complexity of convex hulls and generalization bounds. (English) Zbl 1050.68055

Kivinen, Jyrki (ed.) et al., Computational learning theory. 15th annual conference, COLT 2002, Sydney, Australia, July 8–10, 2002. Proceedings. Berlin: Springer (ISBN 3-540-43836-X). Lect. Notes Comput. Sci. 2375, 59-73 (2002).
Summary: We investigate measures of complexity of function classes based on continuity moduli of Gaussian and Rademacher processes. For Gaussian processes, we obtain bounds on the continuity modulus on the convex hull of a function class in terms of the same quantity for the class itself. We also obtain new bounds on generalization error in terms of localized Rademacher complexities. This allows us to prove new results about generalization performance for convex hulls in terms of characteristics of the base class. As a byproduct, we obtain a simple proof of some of the known bounds on the entropy of convex hulls.
For the entire collection see [Zbl 0992.00045].

MSC:

68Q32 Computational learning theory
PDFBibTeX XMLCite
Full Text: arXiv Link