Computing the MAP assignment in graphical models is generally intractable. As a result, for discrete graphical models, the MAP problem is often approximated using linear programming relaxations. Much research has focused on characterizing when these LP relaxations are tight, and while they are relatively well-understood in the discrete case, only a few results are known for their continuous analog. In this work, we use graph covers to provide necessary and sufficient conditions for continuous MAP relaxations to be tight. We use this characterization to give simple proofs that the relaxation is tight for log-concave decomposable and log-supermodular decomposable models. We conclude by exploring the relationship between these two seemingly distinct classes of functions and providing specific conditions under which the MAP relaxation can and cannot be tight.
Nicholas Ruozzi (UTDallas)
More from the Same Authors
2022 Poster: Boosting the Performance of Generic Deep Neural Network Frameworks with Log-supermodular CRFs »
Hao Xiong · Yangxiao Lu · Nicholas Ruozzi
2017 Poster: Sparse Approximate Conic Hulls »
Greg Van Buskirk · Benjamin Raichel · Nicholas Ruozzi