PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Sufficient conditions for convergence of the sum-product algorithm
Joris Mooij and Bert Kappen
IEEE Transactions on Information Theory, Volume 53, Number 12, pp. 4422-4437, 2007.

Abstract

Abstract—Novel conditions are derived that guarantee convergence of the Sum-Product Algorithm (also known as Loopy Belief Propagation or simply Belief Propagation (BP)) to a unique fixed point, irrespective of the initial messages, for parallel (synchronous) updates. The computational complexity of the conditions is polynomial in the number of variables. In contrast with previously existing conditions, our results are directly applicable to arbitrary factor graphs (with discrete variables) and are shown to be valid also in the case of factors containing zeros, under some additional conditions. The conditions are compared with existing ones, numerically and, if possible, analytically. For binary variables with pairwise interactions, sufficient conditions are derived that take into account local evidence (i.e., single-variable factors) and the type of pair interactions (attractive or repulsive). It is shown empirically that this bound outperforms existing bounds. Index Terms—Contraction, convergence, factor graphs, graphical models, loopy belief propagation, marginalization, message passing, sum–product algorithm.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:4879
Deposited By:Bert Kappen
Deposited On:24 March 2009