Logo image
Belief propagation, Dykstra's algorithm, and iterated information projections
Journal article   Open access   Peer reviewed

Belief propagation, Dykstra's algorithm, and iterated information projections

John Mac Laren Walsh and Phillip Regalia
IEEE transactions on information theory, v 56(8), pp 4114-4128
Aug 2010
url
https://doi.org/10.1109/TIT.2010.2050833View
Published, Version of Record (VoR) Open

Abstract

Information Theory Computer Science
Belief propagation is shown to be an instance of a hybrid between two projection algorithms in the convex programming literature: Dykstra's algorithm with cyclic Bregman projections and an alternating Bregman projections algorithm. Via this connection, new results concerning the convergence and performance of belief propagation can be proven by exploiting the corresponding literature about the two projections algorithms it hybridizes. In this regard, it is identified that the lack of guaranteed convergence for belief propagation results from the asymmetry of its Bregman divergence by proving that when the associated hybrid projection algorithm generalization is used with a symmetric Bregman divergence, it always converges. Additionally, by characterizing factorizations that are close to acyclic in a manner independent of their girth, a new collection of distributions for which belief propagation is guaranteed to perform well is identified using the new projection algorithm framework

Metrics

12 Record Views
6 citations in Scopus

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#11 Sustainable Cities and Communities

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
International collaboration
Web of Science research areas
Computer Science, Information Systems
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
Mathematics, Applied
Logo image