Adaptive and self-averaging Thouless-Anderson-Palmer mean-field theory for probabilistic modeling

Manfred Opper, Ole Winther

    Research output: Contribution to journalJournal articleResearchpeer-review

    606 Downloads (Pure)

    Abstract

    We develop a generalization of the Thouless-Anderson-Palmer (TAP) mean-field approach of disorder physics. which makes the method applicable to the computation of approximate averages in probabilistic models for real data. In contrast to the conventional TAP approach, where the knowledge of the distribution of couplings between the random variables is required, our method adapts to the concrete set of couplings. We show the significance of the approach in two ways: Our approach reproduces replica symmetric results for a wide class of toy models (assuming a nonglassy phase) with given disorder distributions in the thermodynamic limit. On the other hand, simulations on a real data model demonstrate that the method achieves more accurate predictions as compared to conventional TAP approaches.
    Original languageEnglish
    JournalPhysical Review E. Statistical, Nonlinear, and Soft Matter Physics
    Volume64
    Issue number5
    Pages (from-to)056131
    ISSN1063-651X
    DOIs
    Publication statusPublished - 2001

    Bibliographical note

    Copyright (2001) American Physical Society

    Keywords

    • SOLVABLE MODEL
    • OPTIMIZATION
    • EXAMPLES
    • NEURAL NETWORKS
    • TAP
    • CLASSIFICATION
    • SPIN-GLASS
    • BELIEF NETWORKS
    • EQUATIONS

    Fingerprint Dive into the research topics of 'Adaptive and self-averaging Thouless-Anderson-Palmer mean-field theory for probabilistic modeling'. Together they form a unique fingerprint.

    Cite this