Consensus Propagation

TL;DR

Consensus propagation is an asynchronous distributed protocol for averaging in networks, with proven convergence and improved scaling over pairwise methods, extending belief propagation insights beyond simple graph structures.

Contribution

Introduces consensus propagation, a novel asynchronous averaging protocol with convergence guarantees and superior scaling, enriching the belief propagation framework.

Findings

Proves convergence of consensus propagation.

Characterizes convergence rate for regular graphs.

Demonstrates better scaling than pairwise averaging.

Abstract

We propose consensus propagation, an asynchronous distributed protocol for averaging numbers across a network. We establish convergence, characterize the convergence rate for regular graphs, and demonstrate that the protocol exhibits better scaling properties than pairwise averaging, an alternative that has received much recent attention. Consensus propagation can be viewed as a special case of belief propagation, and our results contribute to the belief propagation literature. In particular, beyond singly-connected graphs, there are very few classes of relevant problems for which belief propagation is known to converge.