DGM: A deep learning algorithm for solving partial differential equations

JOURNAL OF COMPUTATIONAL PHYSICS

卷:375

Article

Sirignano, Justin¹  Spiliopoulos, Konstantinos² 

[1] Univ Illinois, Urbana, IL 61801 USA

[2] Boston Univ, Dept Math & Stat, Boston, MA 02215 USA

关键词: Partial differential equations;    Machine learning;    Deep learning;    High-dimensional partial differential equations;   

DOI  :  10.1016/j.jcp.2018.08.029

来源: Elsevier

【 摘 要 】

High-dimensional PDEs have been a longstanding computational challenge. We propose to solve high-dimensional PDEs by approximating the solution with a deep neural network which is trained to satisfy the differential operator, initial condition, and boundary conditions. Our algorithm is meshfree, which is key since meshes become infeasible in higher dimensions. Instead of forming a mesh, the neural network is trained on batches of randomly sampled time and space points. The algorithm is tested on a class of high-dimensional free boundary PDEs, which we are able to accurately solve in up to 200 dimensions. The algorithm is also tested on a high-dimensional Hamilton-Jacobi-Bellman PDE and Burgers' equation. The deep learning algorithm approximates the general solution to the Burgers' equation for a continuum of different boundary conditions and physical conditions (which can be viewed as a high-dimensional space). We call the algorithm a Deep Galerkin Method (DGM) since it is similar in spirit to Galerkin methods, with the solution approximated by a neural network instead of a linear combination of basis functions. In addition, we prove a theorem regarding the approximation power of neural networks for a class of quasilinear parabolic PDEs. (C) 2018 Elsevier Inc. All rights reserved.

【 授权许可】

Free