Exact solution to the random sequential dynamics of a message passing algorithm
Disordered Systems and Neural Networks
2021-03-10 v2 Machine Learning
Abstract
We analyze the random sequential dynamics of a message passing algorithm for Ising models with random interactions in the large system limit. We derive exact results for the two-time correlation functions and the speed of convergence. The {\em de Almedia-Thouless} stability criterion of the static problem is found to be necessary and sufficient for the global convergence of the random sequential dynamics.
Cite
@article{arxiv.2101.01571,
title = {Exact solution to the random sequential dynamics of a message passing algorithm},
author = {Burak Çakmak and Manfred Opper},
journal= {arXiv preprint arXiv:2101.01571},
year = {2021}
}
Comments
Accepted for publication in Physical Review E Letter