Error analysis for physics-informed neural networks (PINNs) approximating Kolmogorov PDEs


Loading...

Date

2022-12

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Physics-informed neural networks approximate solutions of PDEs by minimizing pointwise residuals. We derive rigorous bounds on the error, incurred by PINNs in approximating the solutions of a large class of linear parabolic PDEs, namely Kolmogorov equations that include the heat equation and Black-Scholes equation of option pricing, as examples. We construct neural networks, whose PINN residual (generalization error) can be made as small as desired. We also prove that the total L2-error can be bounded by the generalization error, which in turn is bounded in terms of the training error, provided that a sufficient number of randomly chosen training (collocation) points is used. Moreover, we prove that the size of the PINNs and the number of training samples only grow polynomially with the underlying dimension, enabling PINNs to overcome the curse of dimensionality in this context. These results enable us to provide a comprehensive error analysis for PINNs in approximating Kolmogorov PDEs.

Publication status

published

Editor

Book title

Volume

48 (6)

Pages / Article No.

79

Publisher

Springer

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Physics-informed neural networks; Deep learning; Kolmogorov equations

Organisational unit

03851 - Mishra, Siddhartha / Mishra, Siddhartha check_circle

Notes

Funding

Related publications and datasets

Is new version of: