Learning curves for Gaussian processes models: fluctuations and universality

Dorthe Malzahn, Manfred Opper

    Research output: Chapter in Book/Published conference outputChapter

    Abstract

    Based on a statistical mechanics approach, we develop a method for approximately computing average case learning curves and their sample fluctuations for Gaussian process regression models. We give examples for the Wiener process and show that universal relations (that are independent of the input distribution) between error measures can be derived.
    Original languageEnglish
    Title of host publicationArtificial Neural Networks — ICANN 2001
    EditorsG. Dorffner, H. Bischof, K. Hornik
    Place of PublicationBerlin Heidelberg
    PublisherSpringer
    Pages271-276
    Number of pages6
    Volume2130
    ISBN (Print)9783540424864
    DOIs
    Publication statusPublished - 1 Jan 2001
    EventArtificial Neural Networks 2001 - Vienna, Austria
    Duration: 21 Aug 200125 Aug 2001

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer

    Conference

    ConferenceArtificial Neural Networks 2001
    Abbreviated titleICANN 2001
    CountryAustria
    CityVienna
    Period21/08/0125/08/01

    Bibliographical note

    The original publication is available at www.springerlink.com

    Keywords

    • statistical
    • mechanics
    • computing average
    • learning curves
    • sample fluctuations
    • Gaussian process regression
    • Wiener process
    • universal relations
    • error measures

    Fingerprint

    Dive into the research topics of 'Learning curves for Gaussian processes models: fluctuations and universality'. Together they form a unique fingerprint.

    Cite this