A Bilevel Optimization Method for Inverse Mean-Field Games

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yu, Jiajia, Xiao, Quan, Chen, Tianyi, Lai, Rongjie
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916477307715584
author Yu, Jiajia
Xiao, Quan
Chen, Tianyi
Lai, Rongjie
author_facet Yu, Jiajia
Xiao, Quan
Chen, Tianyi
Lai, Rongjie
contents In this paper, we introduce a bilevel optimization framework for addressing inverse mean-field games, alongside an exploration of numerical methods tailored for this bilevel problem. The primary benefit of our bilevel formulation lies in maintaining the convexity of the objective function and the linearity of constraints in the forward problem. Our paper focuses on inverse mean-field games characterized by unknown obstacles and metrics. We show numerical stability for these two types of inverse problems. More importantly, we, for the first time, establish the identifiability of the inverse mean-field game with unknown obstacles via the solution of the resultant bilevel problem. The bilevel approach enables us to employ an alternating gradient-based optimization algorithm with a provable convergence guarantee. To validate the effectiveness of our methods in solving the inverse problems, we have designed comprehensive numerical experiments, providing empirical evidence of its efficacy.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05539
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Bilevel Optimization Method for Inverse Mean-Field Games
Yu, Jiajia
Xiao, Quan
Chen, Tianyi
Lai, Rongjie
Optimization and Control
In this paper, we introduce a bilevel optimization framework for addressing inverse mean-field games, alongside an exploration of numerical methods tailored for this bilevel problem. The primary benefit of our bilevel formulation lies in maintaining the convexity of the objective function and the linearity of constraints in the forward problem. Our paper focuses on inverse mean-field games characterized by unknown obstacles and metrics. We show numerical stability for these two types of inverse problems. More importantly, we, for the first time, establish the identifiability of the inverse mean-field game with unknown obstacles via the solution of the resultant bilevel problem. The bilevel approach enables us to employ an alternating gradient-based optimization algorithm with a provable convergence guarantee. To validate the effectiveness of our methods in solving the inverse problems, we have designed comprehensive numerical experiments, providing empirical evidence of its efficacy.
title A Bilevel Optimization Method for Inverse Mean-Field Games
topic Optimization and Control
url https://arxiv.org/abs/2401.05539