Simple MAP Inference via Low-Rank Relaxations
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), pp. 3077-3085, 2014.
We focus on the problem of maximum a posteriori (MAP) inference in Markov random fields with binary variables and pairwise interactions. For this common subclass of inference tasks, we consider low-rank relaxations that interpolate between the discrete problem and its full-rank semidefinite relaxation. We develop new theoretical bounds st...More
PPT (Upload PPT)