A Derivative-Free Method for Solving Elliptic Partial Differential Equations with Deep Neural Networks

Abstract

We introduce a deep neural network based method for solving a class of elliptic partial differential equations. We approximate the solution of the PDE with a deep neural network which is trained under the guidance of a probabilistic representation of the PDE in the spirit of the Feynman-Kac formula. The solution is given by an expectation of a martingale process driven by a Brownian motion. As Brownian walkers explore the domain, the deep neural network is iteratively trained using a form of reinforcement learning. Our method is a 'Derivative-Free Loss Method' since it does not require the explicit calculation of the derivatives of the neural network with respect to the input neurons in order to compute the training loss. The advantages of our method are showcased in a series of test problems: a corner singularity problem, an interface problem, and an application to a chemotaxis population model.

arXiv comment25 pages, 4 figures

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Playing Atari with Deep Reinforcement Learning
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Searching for Activation Functions
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Simulator-free Solution of High-Dimensional Stochastic Elliptic Partial Differential Equations using Deep Neural Networks
• Highway and Residual Networks learn Unrolled Iterative Estimation
• A Deep Neural Network Surrogate for High-Dimensional Random Partial Differential Equations
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• Learning across scales - A multiscale method for Convolution Neural Networks

Cited by in corpus (9)

• An overview on deep learning-based approximation methods for partial differential equations
• Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks
• Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations
• Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients
• Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
• Asymptotic preserving scheme for anisotropic elliptic equations with deep neural network
• Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation
• Solving Elliptic Equations with Brownian Motion: Bias Reduction and Temporal Difference Learning
• Hierarchical Learning to Solve Partial Differential Equations Using Physics-Informed Neural Networks