Learning with maximum-entropy distributions

Yishay Mansour; Mariano Schain

doi:10.1145/267460.267499

Learning with maximum-entropy distributions

Yishay Mansour^*
, Mariano Schain

^*Corresponding author for this work

School of Computer Science and AI

Tel Aviv University

Research output: Contribution to conference › Paper › peer-review

Abstract

We are interested in distributions which are derived as a maximum entropy distribution given a 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 we develop an efficient learning algorithm for read-once DNF. We also show how to extend our results to monotone read-k DNF, following the techniques of [HM91].

Original language	English
Pages	201-209
Number of pages	9
DOIs	https://doi.org/10.1145/267460.267499
State	Published - 1997
Event	Proceedings of the 1997 10th Annual Conference on Computational Learning Theory - Nashville, TN, USA Duration: 6 Jul 1997 → 9 Jul 1997

Conference

Conference	Proceedings of the 1997 10th Annual Conference on Computational Learning Theory
City	Nashville, TN, USA
Period	6/07/97 → 9/07/97

Access to Document

10.1145/267460.267499

Cite this

@conference{6deef4d13b8b4e7d822808c88bac912d,

title = "Learning with maximum-entropy distributions",

abstract = "We are interested in distributions which are derived as a maximum entropy distribution given a 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 we develop an efficient learning algorithm for read-once DNF. We also show how to extend our results to monotone read-k DNF, following the techniques of [HM91].",

author = "Yishay Mansour and Mariano Schain",

year = "1997",

doi = "10.1145/267460.267499",

language = "אנגלית",

pages = "201--209",

note = "Proceedings of the 1997 10th Annual Conference on Computational Learning Theory ; Conference date: 06-07-1997 Through 09-07-1997",

}

TY - CONF

T1 - Learning with maximum-entropy distributions

AU - Mansour, Yishay

AU - Schain, Mariano

PY - 1997

Y1 - 1997

N2 - We are interested in distributions which are derived as a maximum entropy distribution given a 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 we develop an efficient learning algorithm for read-once DNF. We also show how to extend our results to monotone read-k DNF, following the techniques of [HM91].

AB - We are interested in distributions which are derived as a maximum entropy distribution given a 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 we develop an efficient learning algorithm for read-once DNF. We also show how to extend our results to monotone read-k DNF, following the techniques of [HM91].

UR - https://www.scopus.com/pages/publications/0030652534

U2 - 10.1145/267460.267499

DO - 10.1145/267460.267499

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:0030652534

SP - 201

EP - 209

T2 - Proceedings of the 1997 10th Annual Conference on Computational Learning Theory

Y2 - 6 July 1997 through 9 July 1997

ER -

Learning with maximum-entropy distributions

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this