Entropic fictitious play for mean field optimization problem - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Machine Learning Research Année : 2023

Entropic fictitious play for mean field optimization problem

Résumé

It is well known that the training of the neural network can be viewed as a mean field optimization problem. In this paper we are inspired by the fictitious play, a classical algorithm in the game theory for learning the Nash equilibria, and propose a new algorithm, different from the conventional gradient-descent ones, to solve the mean field optimization. We rigorously prove its (exponential) convergence, and show some simple numerical examples.

Dates et versions

hal-03909133 , version 1 (21-12-2022)

Identifiants

Citer

Zhenjie Ren, Songbo Wang, Fan Chen. Entropic fictitious play for mean field optimization problem. Journal of Machine Learning Research, 2023, 24 (211), pp.1-36. ⟨hal-03909133⟩
18 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More