Convergence Behavior of Belief Propagation: Estimating Regions of Attraction via Lyapunov Functions

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

In this work, we estimate the regions of attraction for belief propagation. This extends existing stability analysis and provides initial message values for which belief propagation is guaranteed to converge. Our approach utilizes the theory of Lyapunov functions that, however, does not readily yield useful regions of attraction. Therefore, we utilize polynomial sum-of-squares relaxations and provide an algorithm that computes valid Lyapunov functions. This admits a novel way of studying the solution space of belief propagation. Finally, we apply our approach to small-scale models and discuss the effect of the potentials on the regions of attraction.
Original languageEnglish
Title of host publication37th Conference on Uncertainty in Artificial Intelligence
Pages1863-1873
Publication statusPublished - 27 Jul 2021
Event37th Conference on Uncertainty in Artificial Intelligence: UAI 2021 - Virtuell
Duration: 27 Jul 202129 Jul 2021

Publication series

NameProceedings of Machine Learning Research
PublisherML Research Press
Volume161
ISSN (Electronic)2640-3498

Conference

Conference37th Conference on Uncertainty in Artificial Intelligence
CityVirtuell
Period27/07/2129/07/21

Fields of Expertise

  • Information, Communication & Computing

Cite this