The Factored Frontier Algorithm for Approximate Inference in DBNs

The Factored Frontier (FF) algorithm is a simple approximate inference algorithm for Dynamic Bayesian Networks (DBNs). It is very similar to the fully factorized version of the Boyen-Koller (BK) algorithm, but in­ stead of doing an exact update at every step followed by marginalisation (projection), it always works with factored distributions. Hence it can be applied to models for which the exact update step is intractable. We show that FF is equivalent to (one iteration of) loopy belief propagation (LBP) on the origi­ nal DBN, and that BK is equivalent (to one iteration of) LBP on a DBN where we clus­ ter some of the nodes. We then show em­ pirically that by iterating more than once, LBP can improve on the accuracy of both FF and BK. We compare these algorithms on two real-world DBNs: the first is a model of a water treatment plant, and the second is a coupled HMM, used to model freeway traffic.