Exact solution to the random sequential dynamics of a message passing algorithm
| Autor: | Manfred Opper, Burak Çakmak |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Stability criterion Computer science Dynamics (mechanics) Message passing FOS: Physical sciences Disordered Systems and Neural Networks (cond-mat.dis-nn) Condensed Matter - Disordered Systems and Neural Networks 01 natural sciences Machine Learning (cs.LG) 010305 fluids & plasmas Exact solutions in general relativity Exact results 0103 physical sciences Convergence (routing) Ising model Limit (mathematics) 010306 general physics Algorithm |
| Zdroj: | Physical Review E. 103 |
| ISSN: | 2470-0053 2470-0045 |
| Popis: | 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. Accepted for publication in Physical Review E Letter |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|