Empirical Inference

Some Local Measures of Complexity of Convex Hulls and Generalization Bounds

2002

Conference Paper

ei


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.

Author(s): Bousquet, O. and Koltchinskii, V. and Panchenko, D.
Journal: Proceedings of the 15th annual conference on Computational Learning Theory
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{1443,
  title = {Some Local Measures of Complexity of Convex Hulls and Generalization Bounds},
  author = {Bousquet, O. and Koltchinskii, V. and Panchenko, D.},
  journal = {Proceedings of the 15th annual conference on Computational Learning Theory},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  year = {2002},
  doi = {}
}