English
Related papers

Related papers: An operator preconditioning perspective on trainin…

200 papers

Physics Informed Neural Networks (PINNs) have frequently been used for the numerical approximation of Partial Differential Equations (PDEs). The goal of this paper is to construct PINNs along with a computable upper bound of the error,…

Numerical Analysis · Mathematics 2022-12-19 Lewin Ernst , Karsten Urban

Physics-informed neural networks (PINNs) have emerged as a promising deep learning method, capable of solving forward and inverse problems governed by differential equations. Despite their recent advance, it is widely acknowledged that…

Machine Learning · Computer Science 2024-06-11 Franz M. Rohrhofer , Stefan Posch , Clemens Gößnitzer , Bernhard C. Geiger

Physics-informed neural networks (PINNs) have shown promising potential for solving partial differential equations (PDEs) using deep learning. However, PINNs face training difficulties for evolutionary PDEs, particularly for dynamical…

Neural and Evolutionary Computing · Computer Science 2023-12-25 Siqi Chen , Bin Shan , Ye Li

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…

Machine Learning · Computer Science 2025-09-04 Ronald Katende

As a typical application of deep learning, physics-informed neural network (PINN) {has been} successfully used to find numerical solutions of partial differential equations (PDEs), but how to improve the limited accuracy is still a great…

Machine Learning · Computer Science 2022-08-09 Zhi-Yong Zhang , Hui Zhang , Li-Sheng Zhang , Lei-Lei Guo

Discovering hidden physical laws and identifying governing system parameters from sparse observations are central challenges in computational science and engineering. Existing data-driven methods, such as physics-informed neural networks…

Machine Learning · Computer Science 2026-04-16 Dibakar Roy Sarkar , Vijay Kag , Birupaksha Pal , Somdatta Goswami

We propose to enhance the training of physics-informed neural networks (PINNs). To this aim, we introduce nonlinear additive and multiplicative preconditioning strategies for the widely used L-BFGS optimizer. The nonlinear preconditioners…

Numerical Analysis · Mathematics 2024-04-16 Alena Kopaničáková , Hardik Kothari , George Em Karniadakis , Rolf Krause

Physics-informed neural networks (PINNs) [4, 10] are an approach for solving boundary value problems based on differential equations (PDEs). The key idea of PINNs is to use a neural network to approximate the solution to the PDE and to…

Numerical Analysis · Mathematics 2023-05-23 Victorita Dolean , Alexander Heinlein , Siddhartha Mishra , Ben Moseley

Predicting the microstructural and morphological evolution of materials through phase-field modelling is computationally intensive, particularly for high-throughput parametric studies. While neural operators such as the Fourier neural…

Machine Learning · Computer Science 2026-03-11 Nanxi Chen , Airong Chen , Rujin Ma

In this research, the application of the Physics-Informed Neural Network (PINN) model is explored to solve transport equation-based Partial Differential Equations (PDEs). The primary objective is to analyze the impact of different…

Machine Learning · Computer Science 2023-12-04 Akshansh Mishra

Physics-Informed Neural Networks (PINNs) often suffer from slow convergence, training instability, and reduced accuracy on challenging partial differential equations due to the anisotropic and rapidly varying geometry of their loss…

Machine Learning · Computer Science 2026-04-20 Kang An , Chenhao Si , Shiqian Ma , Ming Yan

This work presents a tensorial approach to constructing data-driven reduced-order models corresponding to semi-discrete partial differential equations with canonical Hamiltonian structure. By expressing parameter-varying operators with…

Numerical Analysis · Mathematics 2025-05-14 Arjun Vijaywargiya , Shane A. McQuarrie , Anthony Gruber

We construct the first rigorously justified probabilistic algorithm for recovering the solution operator of a hyperbolic partial differential equation (PDE) in two variables from input-output training pairs. The primary challenge of…

Numerical Analysis · Mathematics 2026-02-03 Christopher Wang , Alex Townsend

A computed approximation of the solution operator to a system of partial differential equations (PDEs) is needed in various areas of science and engineering. Neural operators have been shown to be quite effective at predicting these…

Machine Learning · Computer Science 2024-12-02 Zan Ahmad , Shiyi Chen , Minglang Yin , Avisha Kumar , Nicolas Charon , Natalia Trayanova , Mauro Maggioni

Learning the full family of solutions to parameterized partial differential equations (PDEs) is a central challenge to our ability to model the behavior of heterogeneous systems, with a variety of fundamental and application-oriented…

Computational Physics · Physics 2026-01-26 Milad Panahi , Giovanni Michele Porta , Monica Riva , Alberto Guadagnini

Diffusion-based solvers for partial differential equations (PDEs) are often bottle-necked by slow gradient-based test-time optimization routines that use PDE residuals for loss guidance. They additionally suffer from optimization…

Machine Learning · Computer Science 2025-12-02 Medha Sawhney , Abhilash Neog , Mridul Khurana , Anuj Karpatne

In this paper, we propose a refinement strategy to the well-known Physics-Informed Neural Networks (PINNs) for solving partial differential equations (PDEs) based on the concept of Optimal Transport (OT). Conventional black-box PINNs…

Computational Engineering, Finance, and Science · Computer Science 2021-05-31 Vaishnav Tadiparthi , Raktim Bhattacharya

Inverse problems involving partial differential equations (PDEs) can be seen as discovering a mapping from measurement data to unknown quantities, often framed within an operator learning approach. However, existing methods typically rely…

Numerical Analysis · Mathematics 2025-02-10 Sung Woong Cho , Hwijae Son

Operator learning is a recent development in the simulation of Partial Differential Equations (PDEs) by means of neural networks. The idea behind this approach is to learn the behavior of an operator, such that the resulting neural network…

Numerical Analysis · Mathematics 2025-01-15 Ahmed Abdeljawad , Thomas Dittrich

Physics-informed neural networks (PINNs) have been widely applied to solve partial differential equations (PDEs) by enforcing outputs and gradients of deep models to satisfy target equations. Due to the limitation of numerical computation,…

Machine Learning · Computer Science 2024-10-24 Haixu Wu , Huakun Luo , Yuezhou Ma , Jianmin Wang , Mingsheng Long