Deep Semi-Martingale Optimal Transport

Abstract

We propose two deep neural network-based methods for solving semi-martingale optimal transport problems. The first method is based on a relaxation/penalization of the terminal constraint, and is solved using deep neural networks. The second method is based on the dual formulation of the problem, which we express as a saddle point problem, and is solved using adversarial networks. Both methods are mesh-free and therefore mitigate the curse of dimensionality. We test the performance and accuracy of our methods on several examples up to dimension 10. We also apply the first algorithm to a portfolio optimization problem where the goal is, given an initial wealth distribution, to find an investment strategy leading to a prescribed terminal wealth distribution.

References in corpus (7)

• DGM: A deep learning algorithm for solving partial differential equations
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• A Machine Learning Framework for Solving High-Dimensional Mean Field Game and Mean Field Control Problems
• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• Optimal transportation under controlled stochastic dynamics
• Deep Learning Approximation for Stochastic Control Problems
• Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis