Non-Asymptotic Stability and Consistency Guarantees for Physics-Informed Neural Networks via Coercive Operator Analysis

TL;DR

This paper develops a comprehensive theoretical framework for analyzing the stability and consistency of Physics-Informed Neural Networks (PINNs) using operator coercivity and perturbation theory, supported by empirical validation on various PDEs.

Contribution

It introduces a unified approach to analyze PINNs' stability and consistency through coercive operator analysis, providing non-asymptotic guarantees and practical insights for robust PDE learning.

Findings

Residual minimization ensures convergence under mild regularity.

Stability bounds quantify output perturbation effects.

Sample complexity guarantees for residual generalization.

Abstract

We present a unified theoretical framework for analyzing the stability and consistency of Physics-Informed Neural Networks (PINNs), grounded in operator coercivity, variational formulations, and non-asymptotic perturbation theory. PINNs approximate solutions to partial differential equations (PDEs) by minimizing residual losses over sampled collocation and boundary points. We formalize both operator-level and variational notions of consistency, proving that residual minimization in Sobolev norms leads to convergence in energy and uniform norms under mild regularity. Deterministic stability bounds quantify how bounded perturbations to the network outputs propagate through the full composite loss, while probabilistic concentration results via McDiarmid's inequality yield sample complexity guarantees for residual-based generalization. A unified generalization bound links residual consistency, projection error, and perturbation sensitivity. Empirical results on elliptic, parabolic, and nonlinear PDEs confirm the predictive accuracy of our theoretical bounds across regimes. The framework identifies key structural principles, such as operator coercivity, activation smoothness, and sampling admissibility, that underlie robust and generalizable PINN training, offering principled guidance for the design and analysis of PDE-informed learning systems.