Convergence analysis of the information matrix in Gaussian Belief Propagation

Jian Du; Shaodan Ma; Yik-Chung Wu; Soummya Kar; José M. F. Moura

ICASSP 2017accepted0 citations

Convergence analysis of the information matrix in Gaussian Belief Propagation

Jian Du, Shaodan Ma, Yik-Chung Wu, Soummya Kar, José M. F. Moura

Abstract

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.

BibTeX

@inproceedings{icassp2017_convergenceanaly,
  title = {Convergence analysis of the information matrix in Gaussian Belief Propagation},
  author = {Jian Du and Shaodan Ma and Yik-Chung Wu and Soummya Kar and José M. F. Moura},
  booktitle = {ICASSP 2017},
  year = {2017}
}