DGM: A deep learning algorithm for solving partial differential equations
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, whi...
| Main Authors: | , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Elsevier
2018
|
| _version_ | 1797062415851978752 |
|---|---|
| author | Sirignano, J Spiliopoulos, K |
| author_facet | Sirignano, J Spiliopoulos, K |
| author_sort | Sirignano, J |
| collection | OXFORD |
| description | 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.
|
| first_indexed | 2024-03-06T20:45:13Z |
| format | Journal article |
| id | oxford-uuid:35a8986c-2e56-4652-8a5a-e9cdd1ec391e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T20:45:13Z |
| publishDate | 2018 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:35a8986c-2e56-4652-8a5a-e9cdd1ec391e2022-03-26T13:33:15ZDGM: A deep learning algorithm for solving partial differential equationsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:35a8986c-2e56-4652-8a5a-e9cdd1ec391eEnglishSymplectic ElementsElsevier2018Sirignano, JSpiliopoulos, KHigh-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. |
| spellingShingle | Sirignano, J Spiliopoulos, K DGM: A deep learning algorithm for solving partial differential equations |
| title | DGM: A deep learning algorithm for solving partial differential equations |
| title_full | DGM: A deep learning algorithm for solving partial differential equations |
| title_fullStr | DGM: A deep learning algorithm for solving partial differential equations |
| title_full_unstemmed | DGM: A deep learning algorithm for solving partial differential equations |
| title_short | DGM: A deep learning algorithm for solving partial differential equations |
| title_sort | dgm a deep learning algorithm for solving partial differential equations |
| work_keys_str_mv | AT sirignanoj dgmadeeplearningalgorithmforsolvingpartialdifferentialequations AT spiliopoulosk dgmadeeplearningalgorithmforsolvingpartialdifferentialequations |