Entropic mean-field min-max problems via Best Response flow
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915188629831680 |
|---|---|
| author | Lascu, Razvan-Andrei Majka, Mateusz B. Szpruch, Łukasz |
| author_facet | Lascu, Razvan-Andrei Majka, Mateusz B. Szpruch, Łukasz |
| contents | We investigate the convergence properties of a continuous-time optimization method, the \textit{Mean-Field Best Response} flow, for solving convex-concave min-max games with entropy regularization. We introduce suitable Lyapunov functions to establish exponential convergence to the unique mixed Nash equilibrium. Additionally, we demonstrate the convergence of the fictitious play flow as a by-product of our analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_03033 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Entropic mean-field min-max problems via Best Response flow Lascu, Razvan-Andrei Majka, Mateusz B. Szpruch, Łukasz Optimization and Control Probability We investigate the convergence properties of a continuous-time optimization method, the \textit{Mean-Field Best Response} flow, for solving convex-concave min-max games with entropy regularization. We introduce suitable Lyapunov functions to establish exponential convergence to the unique mixed Nash equilibrium. Additionally, we demonstrate the convergence of the fictitious play flow as a by-product of our analysis. |
| title | Entropic mean-field min-max problems via Best Response flow |
| topic | Optimization and Control Probability |
| url | https://arxiv.org/abs/2306.03033 |