Uniform-in-time propagation of chaos for consensus-based minimax algorithm
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908835740909568 |
|---|---|
| author | Bayraktar, Erhan Ding, Zhiyan Ekren, Ibrahim Zhou, Hongyi |
| author_facet | Bayraktar, Erhan Ding, Zhiyan Ekren, Ibrahim Zhou, Hongyi |
| contents | We study the large-population convergence of a consensus-based algorithm for the saddle point problem proposed by ArXiv: 2212.12334, establishing the uniform-in-time propagation of chaos using a coupling method. Our work shows that the $L^2$-deviation has order $O(N_1^{-1} + N_2^{-1})$ uniformly in time, where $N_1$ and $N_2$ denote the numbers of particles corresponding to the two competing players.
It demonstrates the convergence of the particles to some location near a saddle point of the given objective function, which confirms the computational feasibility of the algorithm.
The main idea behind the proofs is the exponential decay and the concentration of the variances of the particle system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14403 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Uniform-in-time propagation of chaos for consensus-based minimax algorithm Bayraktar, Erhan Ding, Zhiyan Ekren, Ibrahim Zhou, Hongyi Probability 90C47, 90C56, 65C35, Secondary 82C31, 93D50, We study the large-population convergence of a consensus-based algorithm for the saddle point problem proposed by ArXiv: 2212.12334, establishing the uniform-in-time propagation of chaos using a coupling method. Our work shows that the $L^2$-deviation has order $O(N_1^{-1} + N_2^{-1})$ uniformly in time, where $N_1$ and $N_2$ denote the numbers of particles corresponding to the two competing players. It demonstrates the convergence of the particles to some location near a saddle point of the given objective function, which confirms the computational feasibility of the algorithm. The main idea behind the proofs is the exponential decay and the concentration of the variances of the particle system. |
| title | Uniform-in-time propagation of chaos for consensus-based minimax algorithm |
| topic | Probability 90C47, 90C56, 65C35, Secondary 82C31, 93D50, |
| url | https://arxiv.org/abs/2602.14403 |