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.
Physical Review E
- Pub Date:
- March 2021
- Condensed Matter - Disordered Systems and Neural Networks;
- Computer Science - Machine Learning
- Accepted for publication in Physical Review E Letter