## Abstract

It is well known that an arbitrary graphical model of statistical inference defined on a tree, i.e. on a graph without loops, is solved exactly and efficiently by an iterative belief propagation (BP) algorithm convergent to the unique minimum of the so-called Bethe free energy functional. For a general graphical model on a loopy graph, the functional may show multiple minima, the iterative BP algorithm may converge to one of the minima or may not converge at all, and the global minimum of the Bethe free energy functional is not guaranteed to correspond to the optimal maximum likelihood (ML) solution in the zero-temperature limit. However, there are exceptions to this general rule, discussed by Kolmogorov and Wainwright (2005) and by Bayati et al (2006, 2008) in two different contexts, where the zero-temperature version of the BP algorithm finds the ML solution for special models on graphs with loops. These two models share a key feature: their ML solutions can be found by an efficient linear programming (LP) algorithm with a totally uni-modular (TUM) matrix of constraints. Generalizing the two models, we consider a class of graphical models reducible in the zero-temperature limit to LP with TUM constraints. Assuming that a gedanken algorithm, g-BP, for finding the global minimum of the Bethe free energy is available, we show that in the limit of zero temperature, g-BP outputs the ML solution. Our consideration is based on equivalence established between gapless linear programming (LP) relaxation of the graphical model in the T → 0 limit and the respective LP version of the Bethe free energy minimization.

Original language | English (US) |
---|---|

Article number | P10016 |

Journal | Journal of Statistical Mechanics: Theory and Experiment |

Volume | 2008 |

Issue number | 10 |

DOIs | |

State | Published - Oct 1 2008 |

Externally published | Yes |

## Keywords

- Analysis of algorithms
- Exact results
- Messagepassing algorithms
- Spin glasses (theory)

## ASJC Scopus subject areas

- Statistical and Nonlinear Physics
- Statistics and Probability
- Statistics, Probability and Uncertainty