Tractable approximations for probabilistic models: The adaptive Thouless-Anderson-Palmer mean field approach

Manfred Opper, Ole Winther

    Research output: Contribution to journalJournal articleResearchpeer-review

    509 Downloads (Pure)

    Abstract

    We develop an advanced mean held method for approximating averages in probabilistic data models that is based on the Thouless-Anderson-Palmer (TAP) approach of disorder physics. In contrast to conventional TAP. where the knowledge of the distribution of couplings between the random variables is required. our method adapts to the concrete couplings. We demonstrate the validity of our approach, which is so far restricted to models with nonglassy behavior? by replica calculations for a wide class of models as well as by simulations for a real data set.
    Original languageEnglish
    JournalPhysical Review Letters
    Volume86
    Issue number17
    Pages (from-to)3695-3699
    ISSN0031-9007
    DOIs
    Publication statusPublished - 2001

    Bibliographical note

    Copyright (2001) American Physical Society

    Keywords

    • SOLVABLE MODEL
    • NEURAL NETWORKS
    • TAP
    • SPIN-GLASS
    • EQUATIONS

    Fingerprint Dive into the research topics of 'Tractable approximations for probabilistic models: The adaptive Thouless-Anderson-Palmer mean field approach'. Together they form a unique fingerprint.

    Cite this