Exact solution to the random sequential dynamics of a message passing algorithm
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 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.
- Publication:
-
Physical Review E
- Pub Date:
- March 2021
- DOI:
- 10.1103/PhysRevE.103.L030101
- arXiv:
- arXiv:2101.01571
- Bibcode:
- 2021PhRvE.103c0101C
- Keywords:
-
- Condensed Matter - Disordered Systems and Neural Networks;
- Computer Science - Machine Learning
- E-Print:
- Accepted for publication in Physical Review E Letter