Deep Primal-Dual Algorithm for BSDEs: Applications of Machine Learning to CVA and IM

16 Pages Posted: 20 Nov 2017 Last revised: 14 Dec 2017

Date Written: November 15, 2017

Abstract

Building heavily on the recent nice paper [Weinan E-al (2017)], we introduce a primal-dual method for solving BSDEs based on the use of neural networks, stochastic gradient descent and a dual formulation of stochastic control problems. Our algorithm is illustrated with two examples relevant in Mathematical Finance: the pricing of counterparty risk and the computation of initial margin.

Keywords: BSDE, Stochastic Control, Machine Learning, CVA, Initial Margin

Suggested Citation

Henry-Labordere, Pierre, Deep Primal-Dual Algorithm for BSDEs: Applications of Machine Learning to CVA and IM (November 15, 2017). Available at SSRN: https://ssrn.com/abstract=3071506 or http://dx.doi.org/10.2139/ssrn.3071506

Pierre Henry-Labordere (Contact Author)

Natixis - Paris, France ( email )

Paris, Paris 75
France

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,377
Abstract Views
3,672
rank
19,592
PlumX Metrics