Convergence analysis of the information matrix in Gaussian Belief Propagation

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.

[1]  Ali H. Sayed,et al.  Diffusion LMS Strategies for Distributed Estimation , 2010, IEEE Transactions on Signal Processing.

[2]  Dahlia Malkhi,et al.  A unifying framework of rating users and data items in peer-to-peer and social networks , 2008, Peer Peer Netw. Appl..

[3]  Paul H. Siegel,et al.  Gaussian belief propagation solver for systems of linear equations , 2008, 2008 IEEE International Symposium on Information Theory.

[4]  Yik-Chung Wu,et al.  Distributed Clock Skew and Offset Estimation in Wireless Sensor Networks: Asynchronous Algorithm and Convergence Analysis , 2013, IEEE Transactions on Wireless Communications.

[5]  Tao Yang,et al.  A Belief Propagation Based Power Distribution System State Estimator , 2011, IEEE Computational Intelligence Magazine.

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

[7]  Soummya Kar,et al.  Consensus + innovations distributed inference over networks: cooperation and sensing in networked systems , 2013, IEEE Signal Processing Magazine.

[8]  Benjamin Van Roy,et al.  Convergence of Min-Sum Message Passing for Quadratic Optimization , 2006, IEEE Transactions on Information Theory.

[9]  William T. Freeman,et al.  On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs , 2001, IEEE Trans. Inf. Theory.

[10]  Jamie S. Evans,et al.  Distributed Downlink Beamforming With Cooperative Base Stations , 2008, IEEE Transactions on Information Theory.

[11]  Soummya Kar,et al.  Convergence Analysis of Distributed Inference with Vector-Valued Gaussian Belief Propagation , 2016, J. Mach. Learn. Res..

[12]  Yaming Wang,et al.  Fast Distributed Rate Control Algorithm with QoS Support in Ad Hoc Networks , 2010, 2010 IEEE Global Telecommunications Conference GLOBECOM 2010.

[13]  I. Chueshov.  Monotone Random Systems Theory and Applications , 2002 .

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

[15]  Yik-Chung Wu,et al.  Network-Wide Distributed Carrier Frequency Offsets Estimation and Compensation via Belief Propagation , 2013, IEEE Transactions on Signal Processing.

[16]  References , 1971 .

[17]  H. Vincent Poor,et al.  Distributed Linear Parameter Estimation: Asymptotically Efficient Adaptive Strategies , 2011, SIAM J. Control. Optim..

[18]  Frédéric Lehmann,et al.  Iterative Mitigation of Intercell Interference in Cellular Networks Based on Gaussian Belief Propagation , 2012, IEEE Transactions on Vehicular Technology.

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

[20]  Brendan J. Frey.  Local Probability Propagation for Factor Analysis , 1999, NIPS.

[21]  Jian Li,et al.  Computationally Efficient Sparse Bayesian Learning via Belief Propagation , 2009, IEEE Transactions on Signal Processing.

[22]  P. G. Ciarlet,et al.  Introduction to Numerical Linear Algebra and Optimisation , 1989 .

[23]  Roger D. Nussbaum,et al.  A limit set trichotomy for self-mappings of normal cones in banach spaces , 1993 .

[24]  Soummya Kar.  Large scale networked dynamical systems: Distributed inference , 2010 .