Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations

06/15/2017
by   Weinan E, et al.
0

We propose a new algorithm for solving parabolic partial differential equations (PDEs) and backward stochastic differential equations (BSDEs) in high dimension, by making an analogy between the BSDE and reinforcement learning with the gradient of the solution playing the role of the policy function, and the loss function given by the error between the prescribed terminal condition and the solution of the BSDE. The policy function is then approximated by a neural network, as is done in deep reinforcement learning. Numerical results using TensorFlow illustrate the efficiency and accuracy of the proposed algorithms for several 100-dimensional nonlinear PDEs from physics and finance such as the Allen-Cahn equation, the Hamilton-Jacobi-Bellman equation, and a nonlinear pricing model for financial derivatives.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/14/2021

Gradient boosting-based numerical methods for high-dimensional backward stochastic differential equations

In this work we propose a new algorithm for solving high-dimensional bac...
research
12/14/2020

FBSDE based neural network algorithms for high-dimensional quasilinear parabolic PDEs

In this paper, we propose forward and backward stochastic differential e...
research
03/07/2022

A deep branching solver for fully nonlinear partial differential equations

We present a multidimensional deep learning implementation of a stochast...
research
10/21/2021

Deep Reinforcement Learning for Online Control of Stochastic Partial Differential Equations

In many areas, such as the physical sciences, life sciences, and finance...
research
03/28/2023

Adaptive trajectories sampling for solving PDEs with deep learning methods

In this paper, we propose a new adaptive technique, named adaptive traje...
research
05/11/2023

Deep Finite Volume Method for High-Dimensional Partial Differential Equations

In this paper, we propose a new deep learning method, named finite volum...
research
05/13/2018

General solutions for nonlinear differential equations: a deep reinforcement learning approach

Physicists use differential equations to describe the physical dynamical...

Please sign up or login with your details

Forgot password? Click here to reset