Part of Advances in Neural Information Processing Systems 14 (NIPS 2001)
Yee Teh, Max Welling
In this paper we will show that a restricted class of constrained mini- mum divergence problems, named generalized inference problems, can be solved by approximating the KL divergence with a Bethe free energy. The algorithm we derive is closely related to both loopy belief propaga- tion and iterative scaling. This uniļ¬ed propagation and scaling algorithm reduces to a convergent alternative to loopy belief propagation when no constraints are present. Experiments show the viability of our algorithm.