Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs

Abstract

Physics informed neural networks (PINNs) have recently been widely used for robust and accurate approximation of PDEs. We provide rigorous upper bounds on the generalization error of PINNs approximating solutions of the forward problem for PDEs. An abstract formalism is introduced and stability properties of the underlying PDE are leveraged to derive an estimate for the generalization error in terms of the training error and number of training samples. This abstract framework is illustrated with several examples of nonlinear PDEs. Numerical experiments, validating the proposed theory, are also presented.

References in corpus (2)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks

Cited by in corpus (17)

• Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations
• Physics Informed Neural Networks for Simulating Radiative Transfer
• When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?
• Hybrid FEM-NN models: Combining artificial neural networks with the finite element method
• An artificial neural network approach to bifurcating phenomena in computational fluid dynamics
• Physics-informed neural networks (PINNs) for fluid mechanics: A review
• Convergence Rate Analysis for Deep Ritz Method
• On quadrature rules for solving Partial Differential Equations using Neural Networks
• Error estimates of residual minimization using neural networks for linear PDEs
• Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations
• On the Representation of Solutions to Elliptic PDEs in Barron Spaces
• Analysis of Deep Ritz Methods for Laplace Equations with Dirichlet Boundary Conditions
• On the approximation of functions by tanh neural networks
• Physics Informed Neural Networks (PINNs)for approximating nonlinear dispersive PDEs
• Stationary Density Estimation of Itô Diffusions Using Deep Learning
• Learning To Estimate Regions Of Attraction Of Autonomous Dynamical Systems Using Physics-Informed Neural Networks