A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages

Dorthe Malzahn, Manfred Opper, Becker, Becker S. et al. (Editor)

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    52 Downloads (Orbit)

    Abstract

    We apply the replica method of Statistical Physics combined with a variational method to the approximate analytical computation of bootstrap averages for estimating the generalization error. We demonstrate our approach on regression with Gaussian processes and compare our results with averages obtained by Monte-Carlo sampling.
    Original languageEnglish
    Title of host publicationAdvances in Neural Information Processing Systems
    PublisherMIT Press
    Publication date2003
    ISBN (Print)978-026202550-8
    Publication statusPublished - 2003
    Event16th Annual Neural Information Processing Systems Conference - Vancouver, Canada
    Duration: 9 Dec 200214 Dec 2002
    Conference number: 16

    Conference

    Conference16th Annual Neural Information Processing Systems Conference
    Number16
    Country/TerritoryCanada
    CityVancouver
    Period09/12/200214/12/2002

    Fingerprint

    Dive into the research topics of 'A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages'. Together they form a unique fingerprint.

    Cite this