Game on Random Environment, Mean-Field Langevin System, and Neural Networks

Giovanni Conforti (), Anna Kazeykina () and Zhenjie Ren ()
Additional contact information
Giovanni Conforti: Centre de Mathématiques Appliquées, Ecole Polytechnique, Institut Polytechnique de Paris, 91128 Palaiseau Cedex, France
Anna Kazeykina: Laboratoire de Mathématiques d’Orsay, Université Paris-Saclay, 91405 Orsay, France
Zhenjie Ren: Ceremade, Université Paris Dauphine-PSL, 75016 Paris, France

Mathematics of Operations Research, 2023, vol. 48, issue 1, 78-99

Abstract: In this paper, we study a class of games regularized by relative entropy where the players’ strategies are coupled through a random environment. Besides existence and uniqueness of equilibria for such games, we prove, under different sets of hypotheses that the marginal laws of the corresponding mean-field Langevin systems can converge toward the games’ equilibria. As an application, we show that dynamic games fall in this framework by considering the time horizon as environment. Concerning applications, our results allow analysis of stochastic gradient descent algorithms for deep neural networks in the context of supervised learning and for generative adversarial networks.

Keywords: Primary: 37M25; secondary: 60H30; 91A15; mean field Langevin dynamics; Nash equilibrium; neural networks (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/moor.2022.1252 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:ormoor:v:48:y:2023:i:1:p:78-99

Access Statistics for this article

More articles in Mathematics of Operations Research from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().