Tensor networks contraction and the belief propagation algorithm

Abstract

Belief propagation is a well-studied message-passing algorithm that runs over graphical models and can be used for approximate inference and approximation of local marginals. The resulting approximations are equivalent to the Bethe-Peierls approximation of statistical mechanics. Here, we show how this algorithm can be adapted to the world of projected-entangled-pair-state tensor networks and used as an approximate contraction scheme. We further show that the resultant approximation is equivalent to the “mean field” approximation that is used in the simple-update algorithm, thereby showing that the latter is essentially the Bethe-Peierls approximation. This shows that one of the simplest approximate contraction algorithms for tensor networks is equivalent to one of the simplest schemes for approximating marginals in graphical models in general and paves the way for using improvements of belief propagation as tensor networks algorithms.