When is small beautiful?

Amiran Ambroladze, J Shawe-Taylor

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

Abstract

The basic bound on the generalisation error of a PAC learner makes the assumption that a consistent hypothesis exists. This makes it appropriate to apply the method only in the case where we have a guarantee that a consistent hypothesis can be found, something that is rarely possible in real applications. The same problem arises if we decide not to use a hypothesis unless its error is below a prespecified number.
Original languageEnglish
Title of host publicationLecture Notes in Computer Science (Learning Theory and Kernel Machines)
EditorsBernhard Schölkopf, Manfred K. Warmuth
PublisherSpringer
Pages729-730
Volume2777
ISBN (Print)978-3-540-40720-1
DOIs
Publication statusPublished - 2003
Event16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003 - Washington, DC, United States
Duration: 2003 Aug 242003 Aug 27

Publication series

Name
Volume2777
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003
Country/TerritoryUnited States
CityWashington, DC
Period2003/08/242003/08/27

Subject classification (UKÄ)

  • Mathematics

Fingerprint

Dive into the research topics of 'When is small beautiful?'. Together they form a unique fingerprint.

Cite this