CONVERGENCE ANALYSIS OF THE INFORMATION MATRIX IN GAUSSIAN BELIEF PROPAGATION

被引：0

作者：

Du, Jian ^{[1
]}

Ma, Shaodan ^{[2
]}

Wu, Yik-Chung ^{[3
]}

Kar, Soummya ^{[1
]}

Moura, Jose M. F. ^{[1
]}

机构：

[1] Carnegie Mellon Univ, Elect & Comp Engn, Pittsburgh, PA 15213 USA

[2] Univ Macau, Elect & Comp Engn, Macau, Peoples R China

[3] Univ Hong Kong, Elect & Elect Engn, Hong Kong, Hong Kong, Peoples R China

来源：

2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2017年

基金：

美国国家科学基金会;

关键词：

graphical model; belief propagation; large-scale networks; Markov random; GRAPHICAL MODELS; NETWORKS; ALGORITHM;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Gaussian belief propagation (BP) has been widely used for distributed estimation in large-scale networks such as the smart grid, communication networks, and social networks, where local meansurements/observations are scattered over a wide geographical area. However, the convergence of Gaussian BP is still an open issue. In this paper, we consider the convergence of Gaussian BP, focusing in particular on the convergence of the information matrix. We show analytically that the exchanged message information matrix converges for arbitrary positive semidefinite initial value, and its distance to the unique positive definite limit matrix decreases exponentially fast.

引用

页码：4074 / 4078

页数：5

共 50 条

[1] Convergence Analysis of the Variance in Gaussian Belief Propagation
Su, Qinliang
Wu, Yik-Chung
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2014, 62 (19) : 5119 - 5131
[2] Fixing Convergence of Gaussian Belief Propagation
Johnson, Jason K.
Bickson, Danny
Dolev, Danny
[J]. 2009 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, VOLS 1- 4, 2009, : 1674 - +
[3] On Convergence Conditions of Gaussian Belief Propagation
Su, Qinliang
Wu, Yik-Chung
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2015, 63 (05) : 1144 - 1155
[4] Convergence rate analysis of Gaussian belief propagation for Markov networks
Zhang, Zhaorong
Fu, Minyue
[J]. IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2020, 7 (03) : 668 - 673
[5] Convergence Rate Analysis of Gaussian Belief Propagation for Markov Networks
Zhaorong Zhang
Minyue Fu
[J]. IEEE/CAA Journal of Automatica Sinica, 2020, 7 (03) : 668 - 673
[6] CONVERGENCE ANALYSIS OF BELIEF PROPAGATION FOR PAIRWISE LINEAR GAUSSIAN MODELS
Du, Jian
Ma, Shaodan
Wu, Yik-Chung
Kar, Soummya
Moura, Jose M. F.
[J]. 2017 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2017), 2017, : 548 - 552
[7] Convergence Analysis of Gaussian Belief Propagation for Distributed State Estimation
Sui, Tianju
Marelli, Damian E.
Fu, Minyue
[J]. 2015 54TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2015, : 1106 - 1111
[8] Distributed Convergence Verification for Gaussian Belief Propagation
Du, Jian
Kar, Soummya
Moura, Jose M. F.
[J]. 2017 FIFTY-FIRST ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2017, : 1439 - 1443
[9] DISTRIBUTED VERIFICATION OF BELIEF PRECISIONS CONVERGENCE IN GAUSSIAN BELIEF PROPAGATION
Li, Bin
Wu, Nan
Wu, Yik-Chung
[J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 9115 - 9119
[10] On the convergence of Gaussian belief propagation with nodes of arbitrary size
Kamper, Francois
Steel, Sarel J.
du Preez, Johan A.
[J]. Journal of Machine Learning Research, 2019, 20

← 1 2 3 4 5 →