DGM: A deep learning algorithm for solving partial differential equations

By Justin A. Sirignano, Konstantinos Spiliopoulos. 2017

2,539 citations recorded by the source corpus.

High-dimensional PDEs have been a longstanding computational challenge. We propose a deep learning algorithm similar in spirit to Galerkin methods, using a deep neural network instead of linear combinations of basis functions. The PDE is approximated with a deep neural network, which is trained on random batches of spatial points to satisfy the differential operator and boundary conditions. The algorithm is mesh-less, which is key since meshes become infeasible in higher dimensions. Instead of forming a mesh, sequences of spatial points are randomly sampled. We implement the approach for American options (a type of free-boundary PDE which is widely used in finance) in up to 100 dimensions. We call the algorithm a "Deep Galerkin Method (DGM)".

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics, AI for Physical Sciences

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

  1. G. Em Karniadakis
  2. Jian-Xun Wang
  3. Luning Sun
  4. Anima Anandkumar
  5. Lu Lu
  6. Zong-Yi Li
  7. Yang Liu
  8. Paris Perdikaris

In Computer Vision and Pattern Recognition

  1. G. Em Karniadakis
  2. Paris Perdikaris
  3. Yang Liu
  4. Jian-Xun Wang
  5. Sifan Wang
  6. Luning Sun
  7. Lu Lu
  8. Timon Rabczuk

In Statistical and Nonlinear Physics

  1. G. Em Karniadakis
  2. Jian-Xun Wang
  3. Han Gao
  4. Paris Perdikaris
  5. Luning Sun
  6. Lu Lu
  7. Anima Anandkumar
  8. Zong-Yi Li

In AI for Physical Sciences

  1. G. Em Karniadakis
  2. Paris Perdikaris
  3. Maizar Raissi
  4. Jian-Xun Wang
  5. Lu Lu
  6. Luning Sun
  7. Sifan Wang
  8. Han Gao

Citations in the corpus