Belief Propagation Min-Sum Algorithm for Generalized Min-Cost Network Flow

  title={Belief Propagation Min-Sum Algorithm for Generalized Min-Cost Network Flow},
  author={Andrii Riazanov and Yury Maximov and Michael Chertkov},
  journal={2018 Annual American Control Conference (ACC)},
Belief Propagation algorithms are instruments used broadly to solve graphical model optimization and statistical inference problems. In the general case of a loopy Graphical Model, Belief Propagation is a heuristic which is quite successful in practice, even though its empirical success, typically, lacks theoretical guarantees. This paper extends the short list of special cases where correctness and/or convergence of a Belief Propagation algorithm is proven. We generalize the formulation of Min… 



Belief propagation for min-cost network flow: convergence & correctness

This is the first instance where BP is proved to have fully-polynomial running time and a simple modification of the BP algorithm is presented which gives a fully polynomial-time randomized approximation scheme (FPRAS) for MCF.

Linear programming analysis of loopy belief propagation for weighted matching

It is shown that max-product converges to the correct answer if the linear programming (LP) relaxation of the weighted matching problem is tight and does not converge if the LP relaxation is loose.

Understanding belief propagation and its generalizations

It is shown that BP can only converge to a fixed point that is also a stationary point of the Bethe approximation to the free energy, which enables connections to be made with variational approaches to approximate inference.

On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs

It is shown that the assignment based on a fixed point of max-product is a "neighborhood maximum" of the posterior probabilities: the posterior probability of the max- product assignment is guaranteed to be greater than all other assignments in a particular large region around that assignment.

On the Optimality of Tree-reweighted Max-product Message-passing

This paper demonstrates how it is possible to identify part of the optimal solution—i.e., a provably optimal solution for a subset of nodes— without knowing a complete solution, and establishes that for submodular functions, a WTA fixed point always yields a globally optimal solution.

Reverend Bayes on Inference Engines: A Distributed Hierarchical Approach

This paper presents generalizations of Bayes likelihood-ratio updating rule which facilitate an asynchronous propagation of the impacts of new beliefs and/or new evidence in hierarchically organized

Graphical Models, Exponential Families, and Variational Inference

The variational approach provides a complementary alternative to Markov chain Monte Carlo as a general source of approximation methods for inference in large-scale statistical models.

Analytic and Algorithmic Solution of Random Satisfiability Problems

A class of optimization algorithms that can deal with the proliferation of metastable states are introduced; one such algorithm has been tested successfully on the largest existing benchmark of K-satisfiability.

Optimal Listing of Cycles and st-Paths in Undirected Graphs

This work presents the first optimal solution to list all the simple cycles in an undirected graph G, and lets C(G) denote the set of all these cycles (|C(G)| = η).

On the exactness of the cavity method for weighted b-matchings on arbitrary graphs and its relation to linear programs

We consider the general problem of finding the minimum weight b-matching on arbitrary graphs. We prove that, whenever the linear programing relaxation of the problem has no fractional solutions, then