The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems

Abstract

We propose a deep learning based method, the Deep Ritz Method, for numerically solving variational problems, particularly the ones that arise from partial differential equations. The Deep Ritz method is naturally nonlinear, naturally adaptive and has the potential to work in rather high dimensions. The framework is quite simple and fits well with the stochastic gradient descent method used in deep learning. We illustrate the method on several problems including some eigenvalue problems.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• Densely Connected Convolutional Networks
• Solving high-dimensional partial differential equations using deep learning
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations

Cited by in corpus (6)

• Solving the Kolmogorov PDE by means of deep learning
• Weak Form Theory-guided Neural Network (TgNN-wf) for Deep Learning of Subsurface Single and Two-phase Flow
• Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations
• Meta-learning Pseudo-differential Operators with Deep Neural Networks
• Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations
• Towards a regularity theory for ReLU networks -- chain rule and global error estimates