Structured variational methods for distributed inference in wireless ad hoc and sensor networks

Yanbing Zhang, Huaiyu Dai
2009 2009 IEEE International Conference on Acoustics, Speech and Signal Processing  
In this paper, a variational message passing framework is proposed for Markov random fields, which is computationally more efficient and admits wider applicability compared to the belief propagation algorithm. Based on this framework, structured variational methods are explored to take advantage of both the simplicity of variational approximation (for inter-cluster processing) and the accuracy of exact inference (for intra-cluster processing). Its performance is elaborated on a Gaussian Markov
more » ... andom field, through both theoretical analysis and simulation results .
doi:10.1109/icassp.2009.4960198 dblp:conf/icassp/ZhangD09 fatcat:tq6kbfvj7bduzjp6atf7hwm4la