Deep Learning for Mean Field Optimal Transport - Archive ouverte HAL
Proceedings/Recueil Des Communications ESAIM: Proceedings and Surveys Année : 2024

Deep Learning for Mean Field Optimal Transport

Résumé

Mean field control (MFC) problems have been introduced to study social optima in very large populations of strategic agents. The main idea is to consider an infinite population and to simplify the analysis by using a mean field approximation. These problems can also be viewed as optimal control problems for McKean-Vlasov dynamics. They have found applications in a wide range of fields, from economics and finance to social sciences and engineering. Usually, the goal for the agents is to minimize a total cost which consists in the integral of a running cost plus a terminal cost. In this work, we consider MFC problems in which there is no terminal cost but, instead, the terminal distribution is prescribed as in optimal transport problem. By analogy with MFC, we call such problems mean field optimal transport problems (or MFOT for short) since they can be viewed as a generalization of classical optimal transport problems when mean field interactions occur in the dynamics or the running cost function. We propose three numerical methods based on neural networks. The first one is based on directly learning an optimal control. The second one amounts to solve a forward-backward PDE system characterizing the solution. The third one relies on a primal-dual approach. We illustrate these methods with numerical experiments conducted on two families of examples.
Fichier principal
Vignette du fichier
proc2407707.pdf (1.56 Mo) Télécharger le fichier
hal-03762144.pdf (934.22 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03762144 , version 1 (07-03-2023)

Licence

Identifiants

Citer

Sebastian Baudelet, Brieuc Frénais, Mathieu Laurière, Amal Machtalay, Yuchen Zhu. Deep Learning for Mean Field Optimal Transport. ESAIM Proceedings and Surveys, ESAIM: Proceedings and Surveys, 77, pp.145-175, 2024, ⟨10.1051/proc/202477145⟩. ⟨hal-03762144⟩
202 Consultations
63 Téléchargements

Altmetric

Partager

More