On the annealed VC entropy for margin classifiers: A statistical mechanics study

Manfred Opper

    Research output: Chapter in Book/Published conference outputChapter

    Abstract

    Using techniques from Statistical Physics, the annealed VC entropy for hyperplanes in high dimensional spaces is calculated as a function of the margin for a spherical Gaussian distribution of inputs.
    Original languageEnglish
    Title of host publicationAdvances in Kernel Methods - Support vector learning
    EditorsBernhard Scholkopf, Christopher J. C. Burges, Alexander J. Smola
    Place of PublicationCambridge, MA
    PublisherMIT
    Pages117-126
    Number of pages10
    ISBN (Print)0262194163
    Publication statusPublished - 18 Dec 1998

    Bibliographical note

    Copyright of the Massachusetts Institute of Technology Press (MIT Press) Available in Google Books

    Keywords

    • annealed VC entropy
    • hyperplanes
    • high dimensional spaces
    • spherical Gaussian distribution

    Fingerprint

    Dive into the research topics of 'On the annealed VC entropy for margin classifiers: A statistical mechanics study'. Together they form a unique fingerprint.

    Cite this