Abstract— We develop a general framework for MAP estimation in discrete and Gaussian graphical models using Lagrangian relaxation techniques. The key idea is to reformulate an in...
Jason K. Johnson, Dmitry M. Malioutov, Alan S. Wil...
We present a novel dual decomposition approach to MAP inference with highly connected discrete graphical models. Decompositions into cyclic k-fan structured subproblems are shown t...
Rate distortion optimization with Lagrangian formulation is widely used in video encoder control and has proved effective in achieving a good trade-off between coding efficiency a...
This paper describes an algorithm for exact decoding of phrase-based translation models, based on Lagrangian relaxation. The method recovers exact solutions, with certificates of...
The problem of obtaining the maximum a posteriori (map) estimate of a discrete random field is of fundamental importance in many areas of Computer Science. In this work, we build ...