Finding the M most probable configurations using loopy belief propagation

Chen Yanover, Yair Weiss

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

40 Scopus citations

Abstract

Loopy belief propagation (BP) has been successfully used in a num- ber of difficult graphical models to find the most probable configu- ration of the hidden variables. In applications ranging from protein folding to image analysis one would like to find not just the best configuration but rather the top M. While this problem has been solved using the junction tree formalism, in many real world prob- lems the clique size in the junction tree is prohibitively large. In this work we address the problem of finding the M best configura- Tions when exact inference is impossible. We start by developing a new exact inference algorithm for calculat- ing the best configurations that uses only max-marginals. For ap- proximate inference, we replace the max-marginals with the beliefs calculated using max-product BP and generalized BP.We show em-pirically that the algorithm can accurately and rapidly approximate the M best configurations in graphs with hundreds of variables.

Original languageAmerican English
Title of host publicationAdvances in Neural Information Processing Systems 16 - Proceedings of the 2003 Conference, NIPS 2003
PublisherNeural information processing systems foundation
ISBN (Print)0262201526, 9780262201520
StatePublished - 2004
Event17th Annual Conference on Neural Information Processing Systems, NIPS 2003 - Vancouver, BC, Canada
Duration: 8 Dec 200313 Dec 2003

Publication series

NameAdvances in Neural Information Processing Systems
ISSN (Print)1049-5258

Conference

Conference17th Annual Conference on Neural Information Processing Systems, NIPS 2003
Country/TerritoryCanada
CityVancouver, BC
Period8/12/0313/12/03

Fingerprint

Dive into the research topics of 'Finding the M most probable configurations using loopy belief propagation'. Together they form a unique fingerprint.

Cite this