Beyond separability: convergence rate of vanishing viscosity approximations to mean field games via FBSDE stability

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Winston, Du, Qiang, Tang, Wenpin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916946494095360
author Yu, Winston
Du, Qiang
Tang, Wenpin
author_facet Yu, Winston
Du, Qiang
Tang, Wenpin
contents This paper studies the vanishing viscosity approximation to mean field games (MFGs) in $\mathbb{R}^d$ with a nonlocal and possibly non-separable Hamiltonian. We prove that the value function converges at a rate of $\mathcal{O}(β)$, where $β^2$ is the diffusivity constant, which matches the classical convergence rate of vanishing viscosity for Hamilton-Jacobi (HJ) equations. The same rate is also obtained for the approximation of the distribution of players as well as for the gradient of the value function. The proof is a combination of probabilistic and analytical arguments by first analyzing the forward-backward stochastic differential equation associated with the MFG, and then applying a general stability result for HJ equations. Applications of our result to $N$-player games, mean field control, and policy iteration for solving MFGs are also presented.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18529
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond separability: convergence rate of vanishing viscosity approximations to mean field games via FBSDE stability
Yu, Winston
Du, Qiang
Tang, Wenpin
Optimization and Control
Analysis of PDEs
Probability
35Q89, 49L25, 60H10, 91A15, 93E20
This paper studies the vanishing viscosity approximation to mean field games (MFGs) in $\mathbb{R}^d$ with a nonlocal and possibly non-separable Hamiltonian. We prove that the value function converges at a rate of $\mathcal{O}(β)$, where $β^2$ is the diffusivity constant, which matches the classical convergence rate of vanishing viscosity for Hamilton-Jacobi (HJ) equations. The same rate is also obtained for the approximation of the distribution of players as well as for the gradient of the value function. The proof is a combination of probabilistic and analytical arguments by first analyzing the forward-backward stochastic differential equation associated with the MFG, and then applying a general stability result for HJ equations. Applications of our result to $N$-player games, mean field control, and policy iteration for solving MFGs are also presented.
title Beyond separability: convergence rate of vanishing viscosity approximations to mean field games via FBSDE stability
topic Optimization and Control
Analysis of PDEs
Probability
35Q89, 49L25, 60H10, 91A15, 93E20
url https://arxiv.org/abs/2505.18529