Learning with Maximum-Entropy Distributions

Research output: Contribution to journalArticlepeer-review

30 Scopus citations

Abstract

We are interested in distributions which are derived as a maximum entropy distribution from a given set of constraints. More specifically, we are interested in the case where the constraints are the expectation of individual and pairs of attributes. For such a given maximum entropy distribution (with some technical restrictions) we develop an efficient learning algorithm for read-once DNF. We extend our results to monotone read-k DNF following the techniques of (Hancock & Mansour, 1991).

Original languageEnglish
Pages (from-to)123-145
Number of pages23
JournalMachine Learning
Volume45
Issue number2
DOIs
StatePublished - Nov 2001

Funding

Funders
Israel Science Foundation

    Keywords

    • Learning algorithms
    • Maximum entropy
    • PAC-learning

    Fingerprint

    Dive into the research topics of 'Learning with Maximum-Entropy Distributions'. Together they form a unique fingerprint.

    Cite this