$\alpha$ Belief Propagation as Fully Factorized Approximation

Belief propagation (BP) can do exact inference in loop-free graphs, but its performance could be poor in graphs with loops, and the understanding of its solution is limited. This work gives an interpretable belief propagation rule that is actually minimization of a localized alpha-divergence. We term this algorithm as alpha belief propagation (alpha-BP). The performance of alpha-BP is tested in MAP (maximum a posterior) inference problems, where alpha-BP can outperform (loopy) BP by a significant margin even in fully-connected graphs.