Estimates on the generalization error of physics-informed neural networks for approximating PDEs

DOI10.1093/imanum/drab093OpenAlexW4212988227MaRDI QIDQ5879394

Roberto Molinaro, Siddhartha Mishra

Publication date: 1 March 2023

Published in: IMA Journal of Numerical Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.16144

zbMATH Keywords

neural networksquadraturePDEsgeneralization errorstability estimatesPINNs

Mathematics Subject Classification ID

Numerical analysis (65-XX)

Related Items (12)

Some elliptic second order problems and neural network solutions: existence and error estimates ⋮ A priori generalization error analysis of two-layer neural networks for solving high dimensional Schrödinger eigenvalue problems ⋮ Neural control of discrete weak formulations: Galerkin, least squares \& minimal-residual methods with quasi-optimal weights ⋮ Deep neural network solution for finite state mean field game with error estimation ⋮ Physics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithms ⋮ Higher-order error estimates for physics-informed neural networks approximating the primitive equations ⋮ Error analysis of deep Ritz methods for elliptic equations ⋮ Finite basis physics-informed neural networks (FBPINNs): a scalable domain decomposition approach for solving differential equations ⋮ A priori error estimate of deep mixed residual method for elliptic PDEs ⋮ wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws ⋮ Control of partial differential equations via physics-informed neural networks ⋮ Unnamed Item

This page was built for publication: Estimates on the generalization error of physics-informed neural networks for approximating PDEs