Header logo is

The entropy regularization information criterion

2000

Conference Paper

ei


Effective methods of capacity control via uniform convergence bounds for function expansions have been largely limited to Support Vector machines, where good bounds are obtainable by the entropy number approach. We extend these methods to systems with expansions in terms of arbitrary (parametrized) basis functions and a wide range of regularization methods covering the whole range of general linear additive models. This is achieved by a data dependent analysis of the eigenvalues of the corresponding design matrix.

Author(s): Smola, AJ. and Shawe-Taylor, J. and Schölkopf, B. and Williamson, RC.
Book Title: Advances in Neural Information Processing Systems 12
Journal: Advances in Neural Information Processing Systems
Pages: 342-348
Year: 2000
Month: June
Day: 0
Editors: SA Solla and TK Leen and K-R M{\"u}ller
Publisher: MIT Press

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: 13th Annual Neural Information Processing Systems Conference (NIPS 1999)
Event Place: Denver, CO, USA

Address: Cambridge, MA, USA
Digital: 0
ISBN: 0-262-11245-0
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{816,
  title = {The entropy regularization information criterion},
  author = {Smola, AJ. and Shawe-Taylor, J. and Sch{\"o}lkopf, B. and Williamson, RC.},
  journal = {Advances in Neural Information Processing Systems},
  booktitle = {Advances in Neural Information Processing Systems 12},
  pages = {342-348},
  editors = {SA Solla and TK Leen and K-R M{\"u}ller},
  publisher = {MIT Press},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Cambridge, MA, USA},
  month = jun,
  year = {2000},
  doi = {},
  month_numeric = {6}
}