@article{Yoo2024, 
author = {Jihahm Yoo and Haesung Lee},
title = {Robust error estimates of PINN in one-dimensional boundary value problems for linear elliptic equations},
year = {2024},
journal = {AIMS Mathematics},
volume = {9},
number = {10},
pages = {27000-27027},
keywords = {Sobolev spaces, boundary value problems, existence and uniqueness, physics-informed neural networks (PINN), L2-contraction estimates, error estimates},
url = {https://www.sciopen.com/article/10.3934/math.20241314},
doi = {10.3934/math.20241314},
abstract = {In this paper, we study physics-informed neural networks (PINN) to approximate solutions to one-dimensional boundary value problems for linear elliptic equations and establish robust error estimates of PINN regardless of the quantities of the coefficients. In particular, we rigorously demonstrate the existence and uniqueness of solutions using the Sobolev space theory based on a variational approach. Deriving  L2-contraction estimates, we show that the error, defined as the mean square of the differences between the true solution and our trial function at the sample points, is dominated by the training loss. Furthermore, we show that as the quantities of the coefficients for the differential equation increase, the error-to-loss ratio rapidly decreases. Our theoretical and experimental results confirm the robustness of the error regardless of the quantities of the coefficients.}
}