Convergence analysis of Gaussian belief propagation for distributed state estimation

Belief propagation (BP) is a well-celebrated iterative optimization algorithm in statistical learning over network graphs with vast applications in many scientific and engineering fields. This paper studies a fundamental property of this algorithm, namely, its convergence behaviour. Our study is conducted through the problem of distributed state estimation for a networked linear system with additive Gaussian noises, using the weighted least-squares criterion. The corresponding BP algorithm is known as Gaussian BP. Our main contribution is to show that Gaussian BP is guaranteed to converge, under a mild regularity condition. Our result significantly generalizes previous known results on BP's convergence properties, as our study allows general network graphs with cycles and network nodes with random vectors. This result is expected to inspire further investigation of BP and wider applications of BP in distributed estimation and control.

[1]  Gérard Meurant,et al.  A Review on the Inverse of Symmetric Tridiagonal and Block Tridiagonal Matrices , 1992, SIAM J. Matrix Anal. Appl..

[2]  Judea Pearl,et al.  Reverend Bayes on Inference Engines: A Distributed Hierarchical Approach , 1982, AAAI.

[3]  Alain Glavieux,et al.  Reflections on the Prize Paper : "Near optimum error-correcting coding and decoding: turbo codes" , 1998 .

[4]  Kazuyuki Tanaka.  Statistical-mechanical approach to image processing , 2002 .

[5]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .

[6]  Sekhar Tatikonda,et al.  Loopy Belief Propogation and Gibbs Measures , 2002, UAI.

[7]  Hilbert J. Kappen,et al.  Sufficient Conditions for Convergence of the Sum–Product Algorithm , 2005, IEEE Transactions on Information Theory.

[8]  Nanning Zheng,et al.  Stereo Matching Using Belief Propagation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Riccardo Zecchina,et al.  Survey propagation as local equilibrium equations , 2003, ArXiv.

[10]  Yik-Chung Wu,et al.  On Convergence Conditions of Gaussian Belief Propagation , 2015, IEEE Transactions on Signal Processing.

[11]  Yik-Chung Wu,et al.  Convergence Analysis of the Variance in Gaussian Belief Propagation , 2014, IEEE Transactions on Signal Processing.

[12]  X. Jin.  Factor graphs and the Sum-Product Algorithm , 2002 .

[13]  William T. Freeman,et al.  Learning Low-Level Vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[14]  Michael I. Jordan,et al.  Loopy Belief Propagation for Approximate Inference: An Empirical Study , 1999, UAI.

[15]  Sekhar C. Tatikonda,et al.  Convergence of the sum-product algorithm , 2003, Proceedings 2003 IEEE Information Theory Workshop (Cat. No.03EX674).

[16]  Minyue Fu,et al.  Distributed weighted least-squares estimation with fast convergence for large-scale systems , 2015, 52nd IEEE Conference on Decision and Control.

[17]  Tom Heskes,et al.  On the Uniqueness of Loopy Belief Propagation Fixed Points , 2004, Neural Computation.

[18]  John W. Fisher,et al.  Message Errors in Belief Propagation , 2004, NIPS.

[19]  John W. Fisher,et al.  Loopy Belief Propagation: Convergence and Effects of Message Errors , 2005, J. Mach. Learn. Res..

[20]  Minyue Fu,et al.  Stochastic analysis of turbo decoding , 2005, IEEE Transactions on Information Theory.

[21]  Jung-Fu Cheng,et al.  Turbo Decoding as an Instance of Pearl's "Belief Propagation" Algorithm , 1998, IEEE J. Sel. Areas Commun..

[22]  William T. Freeman,et al.  Correctness of Belief Propagation in Gaussian Graphical Models of Arbitrary Topology , 1999, Neural Computation.

[23]  Dmitry M. Malioutov,et al.  Walk-Sums and Belief Propagation in Gaussian Graphical Models , 2006, J. Mach. Learn. Res..

[24]  Riccardo Zecchina,et al.  Survey propagation: An algorithm for satisfiability , 2002, Random Struct. Algorithms.

[25]  Minyue Fu,et al.  A new distributed state estimation technique for power networks , 2013, 2013 American Control Conference.

[26]  Benjamin Van Roy,et al.  Convergence of Min-Sum Message-Passing for Convex Optimization , 2010, IEEE Transactions on Information Theory.