Estimating a mixture of two product distributions

Yoav Freund, Yishay Mansour

Research output: Contribution to conferencePaperpeer-review

Abstract

This study addresses a case involving a mixture of two product distributions over binary vectors. A polynomial time algorithm is given that computes a mixture distribution which is close to the target distribution. The algorithm is efficient both in its sample complexity and its computational complexity.

Original languageEnglish
Pages53-62
Number of pages10
DOIs
StatePublished - 1999
Externally publishedYes
EventProceedings of the 1999 12th Annual Conference on Computational Learning Theory (COLT'99) - Santa Cruz, CA, USA
Duration: 6 Jul 19999 Jul 1999

Conference

ConferenceProceedings of the 1999 12th Annual Conference on Computational Learning Theory (COLT'99)
CitySanta Cruz, CA, USA
Period6/07/999/07/99

Fingerprint

Dive into the research topics of 'Estimating a mixture of two product distributions'. Together they form a unique fingerprint.

Cite this