Worst-case bounds on the quality of max-product fixed-points

Part of Advances in Neural Information Processing Systems 23 (NIPS 2010)

Bibtex Metadata Paper Supplemental


Meritxell Vinyals, Jes\'us Cerquides, Alessandro Farinelli, Juan Rodríguez-aguilar


We study worst-case bounds on the quality of any fixed point assignment of the max-product algorithm for Markov Random Fields (MRF). We start proving a bound independent of the MRF structure and parameters. Afterwards, we show how this bound can be improved for MRFs with particular structures such as bipartite graphs or grids. Our results provide interesting insight into the behavior of max-product. For example, we prove that max-product provides very good results (at least 90% of the optimal) on MRFs with large variable-disjoint cycles (MRFs in which all cycles are variable-disjoint, namely that they do not share any edge and in which each cycle contains at least 20 variables).