Beyond Derivative Pathology of PINNs: Variable Splitting Strategy with Convergence Analysis

TL;DR

This paper identifies a fundamental flaw in PINNs related to derivative regulation, introduces a variable splitting strategy to address it, and proves convergence guarantees for second-order linear PDEs.

Contribution

The paper reveals the derivative pathology in PINNs and proposes a variable splitting method with convergence analysis to improve solution accuracy.

Findings

Variable splitting addresses derivative pathology in PINNs.

The method guarantees convergence for second-order linear PDEs.

Enhanced control over solution derivatives improves PINN performance.

Abstract

Physics-informed neural networks (PINNs) have recently emerged as effective methods for solving partial differential equations (PDEs) in various problems. Substantial research focuses on the failure modes of PINNs due to their frequent inaccuracies in predictions. However, most are based on the premise that minimizing the loss function to zero causes the network to converge to a solution of the governing PDE. In this study, we prove that PINNs encounter a fundamental issue that the premise is invalid. We also reveal that this issue stems from the inability to regulate the behavior of the derivatives of the predicted solution. Inspired by the \textit{derivative pathology} of PINNs, we propose a \textit{variable splitting} strategy that addresses this issue by parameterizing the gradient of the solution as an auxiliary variable. We demonstrate that using the auxiliary variable eludes derivative pathology by enabling direct monitoring and regulation of the gradient of the predicted solution. Moreover, we prove that the proposed method guarantees convergence to a generalized solution for second-order linear PDEs, indicating its applicability to various problems.