The Complexity of Approximating a Bethe Equilibrium

DOI10.1109/TIT.2014.2317487zbMATH Open1360.68790arXiv1109.1724MaRDI QIDQ2986268FDOQ2986268

Authors: Jinwoo Shin 

Publication date: 16 May 2017

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: This paper resolves a common complexity issue in the Bethe approximation of statistical physics and the Belief Propagation (BP) algorithm of artificial intelligence. The Bethe approximation and the BP algorithm are heuristic methods for estimating the partition function and marginal probabilities in graphical models, respectively. The computational complexity of the Bethe approximation is decided by the number of operations required to solve a set of non-linear equations, the so-called Bethe equation. Although the BP algorithm was inspired and developed independently, Yedidia, Freeman and Weiss (2004) showed that the BP algorithm solves the Bethe equation if it converges (however, it often does not). This naturally motivates the following question to understand limitations and empirical successes of the Bethe and BP methods: is the Bethe equation computationally easy to solve? We present a message-passing algorithm solving the Bethe equation in a polynomial number of operations for general binary graphical models of n variables where the maximum degree in the underlying graph is O(log n). Our algorithm can be used as an alternative to BP fixing its convergence issue and is the first fully polynomial-time approximation scheme for the BP fixed-point computation in such a large class of graphical models, while the approximate fixed-point computation is known to be (PPAD-)hard in general. We believe that our technique is of broader interest to understand the computational complexity of the cavity method in statistical physics.

Full work available at URL: https://arxiv.org/abs/1109.1724

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Analysis of algorithms and problem complexity (68Q25) Exactly solvable models; Bethe ansatz (82B23)

Cited In (3)

• Convergence of MCMC and loopy BP in the tree uniqueness region for the hard-core model
• Gauges, loops, and polynomials for partition functions of graphical models
• Diagonal stationary points of the Bethe functional

This page was built for publication: The Complexity of Approximating a Bethe Equilibrium

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2986268)