Loopy belief propagation and Gibbs measures

Authors:
Sekhar C. Tatikonda;Michael I. Jordan
Affiliations:
Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA;Computer Science and Statistics, University of California, Berkeley, Berkeley, CA
Venue:
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
Year:
2002

Citing 2
Cited 23

Introduction to Bayesian Networks

Introduction to Bayesian Networks
Correctness of Local Probability Propagation in Graphical Models with Loops

Neural Computation

On the uniqueness of loopy belief propagation fixed points

Neural Computation
A new look at survey propagation and its generalizations

SODA '05 Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms
Robust message-passing for statistical inference in sensor networks

Proceedings of the 6th international conference on Information processing in sensor networks
Estimating the "Wrong" Graphical Model: Benefits in the Computation-Limited Setting

The Journal of Machine Learning Research
Walk-Sums and Belief Propagation in Gaussian Graphical Models

The Journal of Machine Learning Research
A new look at survey propagation and its generalizations

Journal of the ACM (JACM)
Correlation decay and deterministic FPTAS for counting list-colorings of a graph

SODA '07 Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms
Approximate algorithms for credal networks with binary variables

International Journal of Approximate Reasoning
Graphical Models for Structured Classification, with an Application to Interpreting Images of Protein Subcellular Location Patterns

The Journal of Machine Learning Research
Graphical Models, Exponential Families, and Variational Inference

Foundations and Trends® in Machine Learning
Convexity arguments for efficient minimization of the Bethe and Kikuchi free energies

Journal of Artificial Intelligence Research
A spectral approach to analysing belief propagation for 3-colouring

Combinatorics, Probability and Computing
Message passing for maximum weight independent set

IEEE Transactions on Information Theory
Message quantization in belief propagation: structural results in the low-rate regime

Allerton'09 Proceedings of the 47th annual Allerton conference on Communication, control, and computing
Norm-product belief propagation: primal-dual message-passing for approximate inference

IEEE Transactions on Information Theory
Resource Allocation via Message Passing

INFORMS Journal on Computing
Error bounds between marginal probabilities and beliefs of loopy belief propagation algorithm

MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence
Applications of gibbs measure theory to loopy belief propagation algorithm

MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence
Approximate inference and constrained optimization

UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
Correlation decay and deterministic FPTAS for counting colorings of a graph

Journal of Discrete Algorithms
Resource Allocation via Message Passing

INFORMS Journal on Computing
Message-passing algorithms for quadratic minimization

The Journal of Machine Learning Research
Belief propagation for continuous state spaces: stochastic message-passing with quantitative guarantees

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.12

Visualization

Abstract

We address the question of convergence in the loopy belief propagation (LBP) algorithm. Specifically, we relate convergence of LBP to the existence of a weak limit for a sequence of Gibbs measures defined on the LBP's associated computation tree. Using tools from the theory of Gibbs measures we develop easily testable sufficient conditions for convergence. The failure of convergence of LBP implies the existence of multiple phases for the associated Gibbs specification. These results give new insight into the mechanics of the algorithm.