English

Stochastic Belief Propagation: A Low-Complexity Alternative to the Sum-Product Algorithm

Information Theory 2012-05-28 v2 math.IT Machine Learning

Abstract

The sum-product or belief propagation (BP) algorithm is a widely-used message-passing algorithm for computing marginal distributions in graphical models with discrete variables. At the core of the BP message updates, when applied to a graphical model with pairwise interactions, lies a matrix-vector product with complexity that is quadratic in the state dimension dd, and requires transmission of a (d1)(d-1)-dimensional vector of real numbers (messages) to its neighbors. Since various applications involve very large state dimensions, such computation and communication complexities can be prohibitively complex. In this paper, we propose a low-complexity variant of BP, referred to as stochastic belief propagation (SBP). As suggested by the name, it is an adaptively randomized version of the BP message updates in which each node passes randomly chosen information to each of its neighbors. The SBP message updates reduce the computational complexity (per iteration) from quadratic to linear in dd, without assuming any particular structure of the potentials, and also reduce the communication complexity significantly, requiring only logd\log{d} bits transmission per edge. Moreover, we establish a number of theoretical guarantees for the performance of SBP, showing that it converges almost surely to the BP fixed point for any tree-structured graph, and for graphs with cycles satisfying a contractivity condition. In addition, for these graphical models, we provide non-asymptotic upper bounds on the convergence rate, showing that the \ell_{\infty} norm of the error vector decays no slower than O(1/t)O(1/\sqrt{t}) with the number of iterations tt on trees and the mean square error decays as O(1/t)O(1/t) for general graphs. These analysis show that SBP can provably yield reductions in computational and communication complexities for various classes of graphical models.

Keywords

Cite

@article{arxiv.1111.1020,
  title  = {Stochastic Belief Propagation: A Low-Complexity Alternative to the Sum-Product Algorithm},
  author = {Nima Noorshams and Martin J. Wainwright},
  journal= {arXiv preprint arXiv:1111.1020},
  year   = {2012}
}

Comments

Portions of the results were initially reported at the Allerton Conference on Communications, Control, and Computing (September 2011). The work was also submitted to IEEE Transaction on Information Theory in November 2011

R2 v1 2026-06-21T19:30:48.577Z