Weak Adversarial Networks for High-dimensional Partial Differential Equations

Abstract

Solving general high-dimensional partial differential equations (PDE) is a long-standing challenge in numerical mathematics. In this paper, we propose a novel approach to solve high-dimensional linear and nonlinear PDEs defined on arbitrary domains by leveraging their weak formulations. We convert the problem of finding the weak solution of PDEs into an operator norm minimization problem induced from the weak formulation. The weak solution and the test function in the weak formulation are then parameterized as the primal and adversarial networks respectively, which are alternately updated to approximate the optimal network parameter setting. Our approach, termed as the weak adversarial network (WAN), is fast, stable, and completely mesh-free, which is particularly suitable for high-dimensional PDEs defined on irregular domains where the classical numerical methods based on finite differences and finite elements suffer the issues of slow computation, instability and the curse of dimensionality. We apply our method to a variety of test problems with high-dimensional PDEs to demonstrate its promising performance.

15 pages, 31 figures

References in corpus (12)

• TensorFlow: A system for large-scale machine 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
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• 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
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Accelerating Eulerian Fluid Simulation With Convolutional Networks
• A Deep Neural Network Surrogate for High-Dimensional Random Partial Differential Equations
• Neural Networks Trained to Solve Differential Equations Learn General Representations

Cited by in corpus (66)

• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• Local Extreme Learning Machines and Domain Decomposition for Solving Linear and Nonlinear Partial Differential Equations
• A Method for Representing Periodic Functions and Enforcing Exactly Periodic Boundary Conditions with Deep Neural Networks
• Tackling the Curse of Dimensionality with Physics-Informed Neural Networks
• Deep Learning in Deterministic Computational Mechanics
• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• PFNN: A Penalty-Free Neural Network Method for Solving a Class of Second-Order Boundary-Value Problems on Complex Geometries
• Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions
• An overview on deep learning-based approximation methods for partial differential equations
• Variational Physics Informed Neural Networks: the role of quadratures and test functions
• Numerical Solution of Inverse Problems by Weak Adversarial Networks
• Int-Deep: A Deep Learning Initialized Iterative Method for Nonlinear Problems
• SelectNet: Self-paced Learning for High-dimensional Partial Differential Equations
• Pre-training strategy for solving evolution equations based on physics-informed neural networks
• On Computing the Hyperparameter of Extreme Learning Machines: Algorithm and Application to Computational PDEs, and Comparison with Classical and High-Order Finite Elements
• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• A solver for subsonic flow around airfoils based on physics-informed neural networks and mesh transformation
• Convergence Rate Analysis for Deep Ritz Method
• In-Context Operator Learning with Data Prompts for Differential Equation Problems
• A rate of convergence of Physics Informed Neural Networks for the linear second order elliptic PDEs
• A Modified Batch Intrinsic Plasticity Method for Pre-training the Random Coefficients of Extreme Learning Machines
• Hyperbolic compactification of M-theory and de Sitter quantum gravity
• Hutchinson Trace Estimation for High-Dimensional and High-Order Physics-Informed Neural Networks
• An augmented Lagrangian deep learning method for variational problems with essential boundary conditions
• GAS: A Gaussian Mixture Distribution-Based Adaptive Sampling Method for PINNs
• Deep unfitted Nitsche method for elliptic interface problems
• NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework
• Numerical Approximation of Partial Differential Equations by a Variable Projection Method with Artificial Neural Networks
• Solving time dependent Fokker-Planck equations via temporal normalizing flow
• Neural Parametric Fokker-Planck Equations
• A new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for Deep BSDE solver
• Solving multiscale elliptic problems by sparse radial basis function neural networks
• A Deep Double Ritz Method (D${}^2$RM) for solving Partial Differential Equations using Neural Networks
• Structure Probing Neural Network Deflation
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
• Sparse Gaussian processes for solving nonlinear PDEs
• Towards fast weak adversarial training to solve high dimensional parabolic partial differential equations using XNODE-WAN
• Optimizing Variational Physics-Informed Neural Networks Using Least Squares
• Physics-Aware Neural Implicit Solvers for multiscale, parametric PDEs with applications in heterogeneous media
• Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
• Cell-average based neural network method for hyperbolic and parabolic partial differential equations
• Weak Collocation Regression method: fast reveal hidden stochastic dynamics from high-dimensional aggregate data
• A data-assisted two-stage method for the inverse random source problem
• Solving PDEs on Unknown Manifolds with Machine Learning
• Learning Stochastic Behaviour from Aggregate Data
• Forward and backward problems for coupled subdiffusion systems
• Learning Green's Functions of Linear Reaction-Diffusion Equations with Application to Fast Numerical Solver
• Meta-Auto-Decoder: A Meta-Learning Based Reduced Order Model for Solving Parametric Partial Differential Equations
• Galerkin Neural Networks: A Framework for Approximating Variational Equations with Error Control
• BINet: Learning to Solve Partial Differential Equations with Boundary Integral Networks
• A Deep Learning Based Discontinuous Galerkin Method for Hyperbolic Equations with Discontinuous Solutions and Random Uncertainties
• A reduced order Schwarz method for nonlinear multiscale elliptic equations based on two-layer neural networks
• Analysis of Deep Ritz Methods for Laplace Equations with Dirichlet Boundary Conditions
• Discontinuity-aware KAN-based physics-informed neural networks
• Adaptive Learning on the Grids for Elliptic Hemivariational Inequalities
• Deep learning-based computational method for soft matter dynamics: Deep Onsager-Machlup method
• A Natural Deep Ritz Method for Essential Boundary Value Problems
• Generalization Error Estimates of Machine Learning Methods for Solving High Dimensional Schrödinger Eigenvalue Problems
• Adaptive feature capture method for solving partial differential equations with near singular solutions
• A Machine-Learning Method for Time-Dependent Wave Equations over Unbounded Domains
• A Neural Network with Plane Wave Activation for Helmholtz Equation
• Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximation
• Stationary Density Estimation of Itô Diffusions Using Deep Learning