The entropy regularization information criterion

Alex J. Smola; John Shawe-Taylor; Bernhard Schölkopf; Robert C. Williamson

The entropy regularization information criterion

Alex J. Smola, John Shawe-Taylor, Bernhard Schölkopf, Robert C. Williamson

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › peer-review

1 Citation (Scopus)

Abstract

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.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999
Publisher	Neural Information Processing Systems Foundation
Pages	342-348
Number of pages	7
ISBN (Print)	0262194503, 9780262194501
Publication status	Published - 2000
Event	13th Annual Neural Information Processing Systems Conference, NIPS 1999 - Denver, CO, United States Duration: 29 Nov 1999 → 4 Dec 1999

Publication series

Name	Advances in Neural Information Processing Systems
ISSN (Print)	1049-5258

Conference

Conference	13th Annual Neural Information Processing Systems Conference, NIPS 1999
Country/Territory	United States
City	Denver, CO
Period	29/11/99 → 4/12/99

Cite this

@inproceedings{2b59562d22234fa890eb172b11e73df3,

title = "The entropy regularization information criterion",

abstract = "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 = "Smola, \{Alex J.\} and John Shawe-Taylor and Bernhard Sch{\"o}lkopf and Williamson, \{Robert C.\}",

year = "2000",

language = "English",

isbn = "0262194503",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural Information Processing Systems Foundation",

pages = "342--348",

booktitle = "Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999",

note = "13th Annual Neural Information Processing Systems Conference, NIPS 1999 ; Conference date: 29-11-1999 Through 04-12-1999",

}

Smola, AJ, Shawe-Taylor, J, Schölkopf, B & Williamson, RC 2000, The entropy regularization information criterion. in Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999. Advances in Neural Information Processing Systems, Neural Information Processing Systems Foundation, pp. 342-348, 13th Annual Neural Information Processing Systems Conference, NIPS 1999, Denver, CO, United States, 29/11/99.

The entropy regularization information criterion. / Smola, Alex J.; Shawe-Taylor, John; Schölkopf, Bernhard et al.
Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999. Neural Information Processing Systems Foundation, 2000. p. 342-348 (Advances in Neural Information Processing Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › peer-review

TY - GEN

T1 - The entropy regularization information criterion

AU - Smola, Alex J.

AU - Shawe-Taylor, John

AU - Schölkopf, Bernhard

AU - Williamson, Robert C.

PY - 2000

Y1 - 2000

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/84881055768

M3 - Conference Paper

SN - 0262194503

SN - 9780262194501

T3 - Advances in Neural Information Processing Systems

SP - 342

EP - 348

BT - Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999

PB - Neural Information Processing Systems Foundation

T2 - 13th Annual Neural Information Processing Systems Conference, NIPS 1999

Y2 - 29 November 1999 through 4 December 1999

ER -

The entropy regularization information criterion

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this