Message-Passing Algorithms for Channel Estimation and Decoding Using Approximate Inference

摘要

We design iterative receiver schemes for a generic wireless communicationsystem by treating channel estimation and information decoding as an inferenceproblem in graphical models. We introduce a recently proposed inferenceframework that combines belief propagation (BP) and the mean field (MF)approximation and includes these algorithms as special cases. We also show thatthe expectation propagation and expectation maximization algorithms can beembedded in the BP-MF framework with slight modifications. By applying theconsidered inference algorithms to our probabilistic model, we derive fourdifferent message-passing receiver schemes. Our numerical evaluationdemonstrates that the receiver based on the BP-MF framework and its variantbased on BP-EM yield the best compromise between performance, computationalcomplexity and numerical stability among all candidate algorithms.