Abstract

Tree-reweighted max-product (TRW) message passing [9] is a modified form of the ordinary max-product algorithm for attempting to find minimal energy configurations in Markov random field with cycles. For a TRW fixed point satisfying the strong tree agreement condition, the algorithm outputs a configuration that is provably optimal. In this paper, we focus on the case of binary variables with pairwise couplings, and establish stronger properties of TRW fixed points that satisfy only the milder condition of weak tree agreement (WTA). First, we demonstrate how it is possible to identify part of the optimal solution—i.e., a provably optimal solution for a subset of nodes — without knowing a complete solution. Second, we show that for submodular functions, a WTA fixed point always yields a globally optimal solution. We establish that for binary variables, any WTA fixed point always achieves the global maximum of the linear programming relaxation underlying the TRW method. 1

Citations

5665	Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference - Pearl - 1988
180	BConvergent tree-reweighted message passing for energy minimization - Kolmogorov - 2006
131	Approximation algorithms for classification problems with pairwise relationships: Metric labeling and markov random fields - Kleinberg, Tardos - 1999
130	WT: On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs - Weiss, Freeman
77	Map estimation via agreement on (hyper)trees: Message-passing and linear programming approaches - Wainwright, Jaakkola, et al.
72	Pseudo-boolean optimization - Boros, Hammer
54	Approximation algorithms for the metric labeling problem via a new linear programming formulation - Chekuri, Khanna, et al. - 2001
47	Roof duality, complementation and persistency in quadratic 0-1 optimization - Hammer, Hansen, et al. - 1984
43	Tree Consistency and Bounds on the Performance of the Max–Product Algorithm and its Generalizations - Wainwright, Jaakkola, et al.