DGM: A deep learning algorithm for solving partial differential equations

  title={DGM: A deep learning algorithm for solving partial differential equations},
  author={Justin A. Sirignano and Konstantinos V. Spiliopoulos},
  journal={J. Comput. Phys.},

Figures and Tables from this paper

A deep learning approach for solving Poisson’s equations

A mesh-free deep learning method for solving PDE systems, especially for Poisson’s equations, is studied, which design suitable neural networks that can approximate solutions of a PDE hy formulating it as an optimization problem.

r-Adaptive Deep Learning Method for Solving Partial Differential Equations

An r − adaptive algorithm to solve Partial Differential Equations using a Deep Neural Network and focuses on the latter to solve one- and two-dimensional problems whose solutions are smooth, singular, and/or exhibit strong gradients.

Solving Nonlinear and High-Dimensional Partial Differential Equations via Deep Learning

The main goals of this paper are to elucidate the features, capabilities and limitations of DGM by analyzing aspects of its implementation for a number of different PDEs and PDE systems.

D3M: A Deep Domain Decomposition Method for Partial Differential Equations

A state-of-the-art deep domain decomposition method (D3M) based on the variational principle is proposed for partial differential equations (PDEs) and shows that the D3M approximation solution converges to the exact solution of the underlying PDEs.

Meta-Auto-Decoder for Solving Parametric Partial Differential Equations

Many important problems in science and engineering require solving the so-called parametric partial differential equations (PDEs), i.e., PDEs with different physical parameters, boundary conditions,

The neural network collocation method for solving partial differential equations

This technique could provide a foundation for deep learning methods to be used as preconditioners to traditional methods, where the deep learning method will get close to a solution and traditional solvers can finish the solution.

FinNet: Finite Difference Neural Network for Solving Differential Equations

This work analyzes potential issues with the well-known Physic Informed Neural Network for differential equations with little constraints on the boundary and introduces a novel technique called FinNet, for solving di-erential equations by incorporating finite di-erence into deep learning.

Deep neural network approximation for high-dimensional elliptic PDEs with boundary conditions

It is shown that deep neural networks are capable of representing solutions of the Poisson equation without incurring the curse of dimension and the proofs are based on a probabilistic representation of the solution to thePoisson equation as well as a suitable sampling method.



Accelerating Eulerian Fluid Simulation With Convolutional Networks

This work proposes a data-driven approach that leverages the approximation power of deep-learning with the precision of standard solvers to obtain fast and highly realistic simulations of the Navier-Stokes equations.

Deep relaxation: partial differential equations for optimizing deep neural networks

Stochastic homogenization theory allows us to better understand the convergence of the algorithm, and a stochastic control interpretation is used to prove that a modified algorithm converges faster than SGD in expectation.

Neural-network methods for boundary value problems with irregular boundaries

Two networks are employed: a multilayer perceptron and a radial basis function network to account for the exact satisfaction of the boundary conditions of complex boundary geometry.

Asymptotic Expansion as Prior Knowledge in Deep Learning Method for High dimensional BSDEs

It is demonstrated that the use of asymptotic expansion as prior knowledge in the “deep BSDE solver”, which is a deep learning method for high dimensional BSDEs proposed by Weinan et al. drastically reduces the loss function and accelerates the speed of convergence.

Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations

We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial

Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations

This two part treatise introduces physics informed neural networks – neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations and demonstrates how these networks can be used to infer solutions topartial differential equations, and obtain physics-informed surrogate models that are fully differentiable with respect to all input coordinates and free parameters.

Option pricing with a direct adaptive sparse grid approach

Convergence of numerical schemes for the solution of parabolic stochastic partial differential equations

The extent to which this order of convergence can be improved is investigated, and it is found that better approximations are possible for the case of additive noise, but for multiplicative noise it is shown that no improvements are possible.

Machine Learning Approximation Algorithms for High-Dimensional Fully Nonlinear Partial Differential Equations and Second-order Backward Stochastic Differential Equations

This work proposes a new method for solving high-dimensional fully nonlinear second-order PDEs and shows the efficiency and the accuracy of the method in the cases of a 100-dimensional Black–Scholes–Barenblatt equation, a100-dimensional Hamilton–Jacobi–Bellman equation, and a nonlinear expectation of a 200-dimensional G-Brownian motion.