Consistency of Physics-Informed Neural Networks for Second-Order Elliptic Equations

Yuqian Cheng, Zhuo Chen, Qian Lin

Keywords: consistency, PINN, kernel gradient flow, second-order elliptic equation

Abstract: The physics-informed neural networks (PINNs) are widely applied in solving differential equations. However, few studies have discussed their consistency. In this paper, we consider the consistency of PINNs when applied to second-order elliptic equations with Dirichlet boundary conditions. We first provide the necessary and sufficient condition for the consistency of the physics-informed kernel gradient flow algorithm, and then as a direct corollary, when the neural network is sufficiently wide, we obtain a necessary and sufficient condition for the consistency of PINNs based on the neural tangent kernel theory. We also estimate the non-asymptotic loss bounds of physics-informed kernel gradient flow and PINN under suitable stronger assumptions. Finally, these results inspires us to construct a notable pathological example where the PINN method is inconsistent.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 8830