Convergence of Min-Sum Message Passing for Quadratic Optimization

We establish the convergence of the min-sum message passing algorithm for minimization of a quadratic objective function given a convex decomposition. Our results also apply to the equivalent problem of the convergence of Gaussian belief propagation.

Saved in:

Bibliographic Details
Published in:	IEEE transactions on information theory Vol. 55; no. 5; pp. 2413 - 2423
Main Authors:	Moallemi, C.C., Van Roy, B.
Format:	Journal Article
Language:	English
Published:	New York, NY IEEE 01-05-2009 Institute of Electrical and Electronics Engineers The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Applied sciences Belief propagation Convergence Decentralized optimization Decoding Equivalence Exact sciences and technology Gaussian Graphical models Heuristic algorithms Information theory Information, signal and communications theory Linear programming Message passing message-passing algorithms Minimization Minimization methods Normal distribution Optimization Parity check codes Sum product algorithm Telecommunications and information theory Credal approach Message passing Decentralized system Objective function Decentralized optimization Algorithm Optimization Quadratic function message-passing algorithms
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	We establish the convergence of the min-sum message passing algorithm for minimization of a quadratic objective function given a convex decomposition. Our results also apply to the equivalent problem of the convergence of Gaussian belief propagation.
Bibliography:	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23
ISSN:	0018-9448 1557-9654
DOI:	10.1109/TIT.2009.2016055