Simple MAP Inference via Low-Rank Relaxations

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), pp. 3077-3085, 2014.

Cited by: 15|Bibtex|Views28
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

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

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments