English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  PAC-Bayesian Generic Chaining

Audibert, J.-Y., & Bousquet, O. (2004). PAC-Bayesian Generic Chaining. Advances in Neural Information Processing Systems 16, 1125-1132.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Audibert, J-Y, Author
Bousquet, O1, Author           
Thrun, Editor
S., Editor
Saul, L.K., Editor
Schölkopf, B., Editor
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              

Content

show
hide
Free keywords: -
 Abstract: There exist many different generalization error bounds for classification. Each of these bounds contains an improvement over the others for certain situations. Our goal is to combine these different improvements into a single bound. In particular we combine the PAC-Bayes approach introduced by McAllester, which is interesting for averaging classifiers, with the optimal union bound provided by the generic chaining technique developed by Fernique and Talagrand. This combination is quite natural since the generic chaining is based on the notion of majorizing measures, which can be considered as priors on the set of classifiers, and such priors also arise in the PAC-bayesian setting.

Details

show
hide
Language(s):
 Dates: 2004-06
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: ISBN: 0-262-20152-6
URI: http://nips.cc/Conferences/2003/
BibTex Citekey: 2341
 Degree: -

Event

show
hide
Title: Seventeenth Annual Conference on Neural Information Processing Systems (NIPS 2003)
Place of Event: Vancouver, BC, Canada
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems 16
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Cambridge, MA, USA : MIT Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1125 - 1132 Identifier: -