Convergence analysis of distributed inference with vector-valued Gaussian belief propagation
Du,Jian1; Ma,Shaodan2; Wu,Yik Chung3; Kar,Soummya1; Moura,José M.F.1
Source PublicationJournal of Machine Learning Research
AbstractThis paper considers inference over distributed linear Gaussian models using factor graphs and Gaussian belief propagation (BP). The distributed inference algorithm involves only local computation of the information matrix and of the mean vector, and message passing between neighbors. Under broad conditions, it is shown that the message information matrix converges to a unique positive definite limit matrix for arbitrary positive semidefinite initialization, and it approaches an arbitrarily small neighborhood of this limit matrix at an exponential rate. A necessary and sufficient convergence condition for the belief mean vector to converge to the optimal centralized estimator is provided under the assumption that the message information matrix is initialized as a positive semidefinite matrix. Further, it is shown that Gaussian BP always converges when the underlying factor graph is given by the union of a forest and a single loop. The proposed convergence condition in the setup of distributed linear Gaussian models is shown to be strictly weaker than other existing convergence conditions and requirements, including the Gaussian Markov random field based walk-summability condition, and applicable to a large class of scenarios.
KeywordGraphical Model Large-Scale Networks Linear Gaussian Model Markov Random Field Walk-summability
URLView the original
Fulltext Access
Document TypeJournal article
CollectionUniversity of Macau
Affiliation1.Department of Electrical and Computer Engineering,Carnegie Mellon University,Pittsburgh,15213,United States
2.Department of Electrical and Computer Engineering,University of Macau,Taipa, Macau,Avenida da Universidade,Macao
3.Department of Electrical and Electronic Engineering,University of Hong Kong,Hong Kong,Pokfulam Road,Hong Kong
Recommended Citation
GB/T 7714
Du,Jian,Ma,Shaodan,Wu,Yik Chung,et al. Convergence analysis of distributed inference with vector-valued Gaussian belief propagation[J]. Journal of Machine Learning Research,2018,18:1-38.
APA Du,Jian,Ma,Shaodan,Wu,Yik Chung,Kar,Soummya,&Moura,José M.F..(2018).Convergence analysis of distributed inference with vector-valued Gaussian belief propagation.Journal of Machine Learning Research,18,1-38.
MLA Du,Jian,et al."Convergence analysis of distributed inference with vector-valued Gaussian belief propagation".Journal of Machine Learning Research 18(2018):1-38.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Du,Jian]'s Articles
[Ma,Shaodan]'s Articles
[Wu,Yik Chung]'s Articles
Baidu academic
Similar articles in Baidu academic
[Du,Jian]'s Articles
[Ma,Shaodan]'s Articles
[Wu,Yik Chung]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Du,Jian]'s Articles
[Ma,Shaodan]'s Articles
[Wu,Yik Chung]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.