English
Related papers

Related papers: PINNs error estimates for nonlinear equations in $…

200 papers

Physics-informed neural networks (PINNs) provide a means of obtaining approximate solutions of partial differential equations and systems through the minimisation of an objective function which includes the evaluation of a residual function…

Machine Learning · Computer Science 2024-10-08 Jose Florido , He Wang , Amirul Khan , Peter K. Jimack

Physics-Informed Neural Networks (PINNs) are a kind of deep-learning-based numerical solvers for partial differential equations (PDEs). Existing PINNs often suffer from failure modes of being unable to propagate patterns of initial…

Machine Learning · Computer Science 2025-08-19 Chenhui Xu , Dancheng Liu , Yuting Hu , Jiajie Li , Ruiyang Qin , Qingxiao Zheng , Jinjun Xiong

In this work, we propose and analyze a residual-minimization strategy for the numerical solution of nonlinear PDEs posed in Banach spaces. Given a finite-dimensional trial space and a suitably enriched discrete test space (of higher…

Numerical Analysis · Mathematics 2026-04-02 Ignacio Muga , Jorge Perera , Sergio Rojas , Ricardo Ruiz-Baier

We shall prove a rearrangement inequality in probability measure spaces in order to obtain sharp Leibniz-type rules of mean oscillations in Lp-spaces and rearrangement invariant Banach function spaces.

Functional Analysis · Mathematics 2017-08-31 Zoltan Leka

Physics-Informed Neural Networks (PINN) are algorithms from deep learning leveraging physical laws by including partial differential equations together with a respective set of boundary and initial conditions as penalty terms into their…

Machine Learning · Computer Science 2025-09-30 Rafael Bischof , Michael Kraus

We consider the subcritical nonlinear Schr\"odinger (NLS) in dimension one posed on the unbounded real line. Several previous works have considered the deep neural network approximation of NLS solutions from the numerical and theoretical…

Analysis of PDEs · Mathematics 2025-06-27 Miguel Á. Alejo , Lucrezia Cossetti , Luca Fanelli , Claudio Muñoz , Nicolás Valenzuela

Physics-Informed Neural Networks present a novel approach in SciML that integrates physical laws in the form of partial differential equations directly into the NN through soft constraints in the loss function. This work studies the…

Neural and Evolutionary Computing · Computer Science 2026-02-17 Suhas Suresh Bharadwaj , Reuben Thomas Thovelil

Sharp $L^\infty$ estimates are obtained for general classes of fully non-linear PDE's on non-K\"ahler manifolds, complementing the theory developed earlier by the authors in joint work with F. Tong for the K\"ahler case. The key idea is…

Differential Geometry · Mathematics 2023-03-01 Bin Guo , Duong H. Phong

We propose an adaptive sampling method for the training of Physics Informed Neural Networks (PINNs) which allows for sampling based on an arbitrary problem-specific heuristic which may depend on the network and its gradients. In particular…

Numerical Analysis · Mathematics 2026-04-08 Kevin Buck , Woojeong Kim

Physics-informed neural networks (PINNs) are extensively employed to solve partial differential equations (PDEs) by ensuring that the outputs and gradients of deep learning models adhere to the governing equations. However, constrained by…

Machine Learning · Computer Science 2025-07-21 Chenhao Si , Ming Yan

This is an attempt to build Banach space valued theory for certain singular integrals on Hamming cube. Of course all estimates below are dimension independent, and we tried to find ultimate sharp assumptions on the Banach space for a…

Functional Analysis · Mathematics 2022-04-27 Paata Ivanisvili , Alexander Volberg

Physics-Informed Neural Networks (PINNs) have been widely used to obtain solutions to various physical phenomena modeled as Differential Equations. As PINNs are not naturally equipped with mechanisms for Uncertainty Quantification, some…

Machine Learning · Computer Science 2025-06-05 Pablo Flores , Olga Graf , Pavlos Protopapas , Karim Pichara

This paper presents intersection of Physics informed neural networks (PINNs) and Lie symmetry group to enhance the accuracy and efficiency of solving partial differential equation (PDEs). Various methods have been developed to solve these…

Analysis of PDEs · Mathematics 2025-10-01 Ali Haider Shah , Naveed R. Butt , Asif Ahmad , Muhammad Omer Bin Saeed

In this paper, local H\"older regularization is incorporated into a physics-informed neural networks (PINNs) framework for solving elliptic partial differential equations (PDEs). Motivated by the interior regularity properties of linear…

Numerical Analysis · Mathematics 2025-10-31 Qirui Zhou , Jiebao Sun , Yi Ran , Boying Wu

This paper focuses on the PINNs algorithm by proposing the ALM-PINNs computational framework to solve various nonlinear partial differential equations and corresponding parameters identification problems. The numerical solutions obtained by…

Numerical Analysis · Mathematics 2024-10-15 Yimeng Tian , Dinghua Xu

In this paper we relate the geometry of Banach spaces to the theory of differential equations, apparently in a new way. We will construct Banach function space norms arising as weak solutions to ordinary differential equations of first…

Functional Analysis · Mathematics 2016-08-30 Jarno Talponen

The main contribution of this paper is to develop a hierarchical Bayesian formulation of PINNs for linear inverse problems, which is called BPINN-IP. The proposed methodology extends PINN to account for prior knowledge on the nature of the…

Machine Learning · Statistics 2026-02-05 Ali Mohammad-Djafari

In general $n$-dimensional simplicial meshes, we propose a family of interior penalty nonconforming finite element methods for $2m$-th order partial differential equations, where $m \geq 0$ and $n \geq 1$. For this family of nonconforming…

Numerical Analysis · Mathematics 2024-12-18 Shuonan Wu , Jinchao Xu

This work investigates the use of shallow physics-informed neural networks (PINNs) for solving forward and inverse problems of nonlinear partial differential equations (PDEs). By reformulating PINNs as nonlinear systems, the…

Numerical Analysis · Mathematics 2026-02-12 Muhammad Luthfi Shahab , Imam Mukhlash , Hadi Susanto

Physics informed neural networks (PINNs) are nowadays used as efficient machine learning methods for solving differential equations. However, vanilla-PINNs fail to learn complex problems as ones involving stiff ordinary differential…

Computational Physics · Physics 2023-04-18 Hubert Baty