Game on Random Environment, Mean-field Langevin System and Neural Networks - Département de mathématiques appliquées Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

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

Résumé

In this paper we study a type of games regularized by the relative entropy, where the players' strategies are coupled through a random environment variable. Besides the existence and the uniqueness of equilibria of such games, we prove that the marginal laws of the corresponding mean-field Langevin systems can converge towards the games' equilibria in different settings. As applications, the dynamic games can be treated as games on a random environment when one treats the time horizon as the environment. In practice, our results can be applied to analysing the stochastic gradient descent algorithm for deep neural networks in the context of supervised learning as well as for the generative adversarial networks.
Fichier principal
Vignette du fichier
MFL_Game_arxiv.pdf (439.58 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02532096 , version 1 (04-04-2020)
hal-02532096 , version 2 (15-04-2020)

Identifiants

  • HAL Id : hal-02532096 , version 2

Citer

Giovanni Conforti, Anna Kazeykina, Zhenjie Ren. Game on Random Environment, Mean-field Langevin System and Neural Networks. 2020. ⟨hal-02532096v2⟩
324 Consultations
78 Téléchargements

Partager

Gmail Facebook X LinkedIn More