A Spectral Approach to Analyzing Belief Propagation for 3-Coloring
Computational Complexity
2017-11-17 v1 Artificial Intelligence
Discrete Mathematics
Abstract
Contributing to the rigorous understanding of BP, in this paper we relate the convergence of BP to spectral properties of the graph. This encompasses a result for random graphs with a ``planted'' solution; thus, we obtain the first rigorous result on BP for graph coloring in the case of a complex graphical structure (as opposed to trees). In particular, the analysis shows how Belief Propagation breaks the symmetry between the possible permutations of the color classes.
Keywords
Cite
@article{arxiv.0712.0171,
title = {A Spectral Approach to Analyzing Belief Propagation for 3-Coloring},
author = {Amin Coja-Oghlan and Elchanan Mossel and Dan Vilenchik},
journal= {arXiv preprint arXiv:0712.0171},
year = {2017}
}