Neural networks-based algorithms for stochastic control and PDEs in finance * - Réseau de recherche en Théorie des Systèmes Distribués, Modélisation, Analyse et Contrôle des Systèmes Accéder directement au contenu
Chapitre D'ouvrage Année : 2021

Neural networks-based algorithms for stochastic control and PDEs in finance *

Résumé

This paper presents machine learning techniques and deep reinforcement learningbased algorithms for the efficient resolution of nonlinear partial differential equations and dynamic optimization problems arising in investment decisions and derivative pricing in financial engineering. We survey recent results in the literature, present new developments, notably in the fully nonlinear case, and compare the different schemes illustrated by numerical tests on various financial applications. We conclude by highlighting some future research directions.
Fichier principal
Vignette du fichier
ArXivHandbook.pdf (1.36 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03115503 , version 1 (19-01-2021)
hal-03115503 , version 2 (15-04-2021)

Identifiants

Citer

Maximilien Germain, Huyên Pham, Xavier Warin. Neural networks-based algorithms for stochastic control and PDEs in finance *. A. Capponi. and C.A. Lehalle. Machine Learning And Data Sciences For Financial Markets: A Guide To Contemporary Practices, Cambridge University Press, In press. ⟨hal-03115503v2⟩
331 Consultations
786 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More