On the convergence of physics informed neural networks for linear second-order elliptic and parabolic type PDEs

Abstract

Physics informed neural networks (PINNs) are deep learning based techniques for solving partial differential equations (PDEs) encounted in computational science and engineering. Guided by data and physical laws, PINNs find a neural network that approximates the solution to a system of PDEs. Such a neural network is obtained by minimizing a loss function in which any prior knowledge of PDEs and data are encoded. Despite its remarkable empirical success in one, two or three dimensional problems, there is little theoretical justification for PINNs. As the number of data grows, PINNs generate a sequence of minimizers which correspond to a sequence of neural networks. We want to answer the question: Does the sequence of minimizers converge to the solution to the PDE? We consider two classes of PDEs: linear second-order elliptic and parabolic. By adapting the Schauder approach and the maximum principle, we show that the sequence of minimizers strongly converges to the PDE solution in $C^0$. Furthermore, we show that if each minimizer satisfies the initial/boundary conditions, the convergence mode becomes $H^1$. Computational examples are provided to illustrate our theoretical findings. To the best of our knowledge, this is the first theoretical work that shows the consistency of PINNs.

Cited by in corpus (35)

• Self-adaptive loss balanced Physics-informed neural networks for the incompressible Navier-Stokes equations
• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations
• Multi-Objective Loss Balancing for Physics-Informed Deep Learning
• Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations
• When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?
• Multilevel domain decomposition-based architectures for physics-informed neural networks
• An artificial neural network approach to bifurcating phenomena in computational fluid dynamics
• Pre-training strategy for solving evolution equations based on physics-informed neural networks
• A cusp-capturing PINN for elliptic interface problems
• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• A Deep Learning approach to Reduced Order Modelling of Parameter Dependent Partial Differential Equations
• Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks
• Physics-enhanced deep surrogates for partial differential equations
• Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning
• Recipes for when Physics Fails: Recovering Robust Learning of Physics Informed Neural Networks
• Learning Specialized Activation Functions for Physics-informed Neural Networks
• A Framework Based on Symbolic Regression Coupled with eXtended Physics-Informed Neural Networks for Gray-Box Learning of Equations of Motion from Data
• On Physics-Informed Neural Networks for Quantum Computers
• Physics-Informed Deep Learning of Rate-and-State Fault Friction
• Learning thermoacoustic interactions in combustors using a physics-informed neural network
• Using physics-informed neural networks to compute quasinormal modes
• SVD-PINNs: Transfer Learning of Physics-Informed Neural Networks via Singular Value Decomposition
• Neural Networks to solve Partial Differential Equations: a Comparison with Finite Elements
• Physics-informed neural networks for learning the homogenized coefficients of multiscale elliptic equations
• Deep learning for full-field ultrasonic characterization
• Physics-informed neural network method for modelling beam-wall interactions
• LSA-PINN: Linear Boundary Connectivity Loss for Solving PDEs on Complex Geometry
• An efficient neural-network and finite-difference hybrid method for elliptic interface problems with applications
• Forecasting and predicting stochastic agent-based model data with biologically-informed neural networks
• Runge-Kutta Physics Informed Neural Networks: Formulation and Analysis
• Deep Ritz-Finite Element methods: Neural Network Methods trained with Finite Elements
• Fixed-budget online adaptive learning for physics-informed neural networks. Towards parameterized problem inference
• XNet-Enhanced Deep BSDE Method and Numerical Analysis