Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs
From MaRDI portal
Publication:6344005
DOI10.1093/IMANUM/DRAB093arXiv2006.16144MaRDI QIDQ6344005FDOQ6344005
Siddhartha Mishra, Roberto Molinaro
Publication date: 29 June 2020
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.
This page was built for publication: Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6344005)
