Abstract

Approximate MAP inference in graphical models is an important and challenging problem for many domains including computer vision, computational biology and natural language understanding. Current state-of-theart approaches employ convex relaxations of these problems as surrogate objectives, but only provide weak running time guarantees. In this paper, we develop an approximate inference algorithm that is both efficient and has strong theoretical guarantees. Specifically, our algorithm is guaranteed to converge to an -accurate
solution of the convex relaxation in time. We demonstrate our approach on synthetic and real-world problems and show that it outperforms current stateof-the-art techniques.