Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions

Abstract

We propose a new method to deal with the essential boundary conditions encountered in the deep learning-based numerical solvers for partial differential equations. The trial functions representing by deep neural networks are non-interpolatory, which makes the enforcement of the essential boundary conditions a nontrivial matter. Our method resorts to Nitsche's variational formulation to deal with this difficulty, which is consistent, and does not require significant extra computational costs. We prove the error estimate in the energy norm and illustrate the method on several representative problems posed in at most 100 dimension.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• DGM: A deep learning algorithm for solving partial differential equations
• 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
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• Weak Adversarial Networks for High-dimensional Partial Differential Equations
• Multi-scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains
• Deep Network Approximation for Smooth Functions
• Multi-scale Deep Neural Network (MscaleDNN) Methods for Oscillatory Stokes Flows in Complex Domains
• BCR-Net: a neural network based on the nonstandard wavelet form
• Quasi-Monte Carlo sampling for machine-learning partial differential equations

Cited by in corpus (30)

• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• Multi-scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains
• PFNN: A Penalty-Free Neural Network Method for Solving a Class of Second-Order Boundary-Value Problems on Complex Geometries
• A cusp-capturing PINN for elliptic interface problems
• BINN: A deep learning approach for computational mechanics problems based on boundary integral equations
• Deep energy method in topology optimization applications
• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
• An augmented Lagrangian deep learning method for variational problems with essential boundary conditions
• Error estimates of residual minimization using neural networks for linear PDEs
• MOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEs
• Deep unfitted Nitsche method for elliptic interface problems
• Deep-learning quasi-particle masses from QCD equation of state
• Deep Ritz Method with Adaptive Quadrature for Linear Elasticity
• A priori and a posteriori error estimates for the Deep Ritz method applied to the Laplace and Stokes problem
• Structure Probing Neural Network Deflation
• Reproducing Activation Function for Deep Learning
• An efficient neural-network and finite-difference hybrid method for elliptic interface problems with applications
• Feature Engineering with Regularity Structures
• Implicit bias with Ritz-Galerkin method in understanding deep learning for solving PDEs
• Gradient Flow Based Phase-Field Modeling Using Separable Neural Networks
• A Neural Solver for Variational Problems on CAD Geometries with Application to Electric Machine Simulation
• A deep implicit-explicit minimizing movement method for option pricing in jump-diffusion models
• Asymptotic-Preserving Neural Networks for Multiscale Time-Dependent Linear Transport Equations
• Deep Ritz-Finite Element methods: Neural Network Methods trained with Finite Elements
• Generalization Error Analysis of Neural networks with Gradient Based Regularization
• Error bounds for PDE-regularized learning
• A Natural Deep Ritz Method for Essential Boundary Value Problems
• A pre-training deep learning method for simulating the large bending deformation of bilayer plates
• Lower Bound on the Representation Complexity of Antisymmetric Tensor Product Functions