English
Related papers

Related papers: Error estimates for physics informed neural networ…

200 papers

We analyze neural network solutions to partial differential equations obtained with Physics Informed Neural Networks. In particular, we apply tools of classical finite element error analysis to obtain conclusions about the error of the Deep…

Numerical Analysis · Mathematics 2022-10-24 Piotr Minakowski , Thomas Richter

Efficient algorithms for solving high-dimensional partial differential equations (PDEs) has been an exceedingly difficult task for a long time, due to the curse of dimensionality. We extend the forward-backward stochastic neural networks…

Numerical Analysis · Mathematics 2024-06-21 Yangtao Deng , Qiaolin He

Neural Network Differential Equation (NN DE) solvers have surged in popularity due to a combination of factors: computational advances making their optimization more tractable, their capacity to handle high dimensional problems, easy…

Numerical Analysis · Mathematics 2021-11-19 Akshunna S. Dogra

This work compares the advantages and limitations of the Finite Difference Method with Physics-Informed Neural Networks, showing where each can best be applied for different problem scenarios. Analysis on the L2 relative error based on…

General Mathematics · Mathematics 2025-02-06 Batyr Sharimbayev , Shirali Kadyrov , Aleksei Kavokin

Physics-informed neural networks and operator networks have shown promise for effectively solving equations modeling physical systems. However, these networks can be difficult or impossible to train accurately for some systems of equations.…

Machine Learning · Computer Science 2023-11-22 Amanda A Howard , Sarah H Murphy , Shady E Ahmed , Panos Stinis

We derive upper bounds on the complexity of ReLU neural networks approximating the solution maps of parametric partial differential equations. In particular, without any knowledge of its concrete shape, we use the inherent…

Numerical Analysis · Mathematics 2020-05-15 Gitta Kutyniok , Philipp Petersen , Mones Raslan , Reinhold Schneider

We perform scalable approximate inference in continuous-depth Bayesian neural networks. In this model class, uncertainty about separate weights in each layer gives hidden units that follow a stochastic differential equation. We demonstrate…

Machine Learning · Statistics 2022-02-01 Winnie Xu , Ricky T. Q. Chen , Xuechen Li , David Duvenaud

Physics-informed neural networks (PINNs) have emerged as a promising approach to solving partial differential equations (PDEs) using neural networks, particularly in data-scarce scenarios, due to their unsupervised training capability.…

Machine Learning · Computer Science 2025-03-25 Edgar Torres , Jonathan Schiefer , Mathias Niepert

We present new error estimates for the finite volume and finite difference methods applied to the compressible Navier-Stokes equations. The main innovative ingredients of the improved error estimates are a refined consistency analysis…

Numerical Analysis · Mathematics 2022-05-10 Eduard Feireisl , Mária Lukáčová-Medviďová , Bangwei She

Whilst the partial differential equations that govern the dynamics of our world have been studied in great depth for centuries, solving them for complex, high-dimensional conditions and domains still presents an incredibly large…

Machine Learning · Computer Science 2023-03-07 Edward Small

We introduce an evidence-driven Bayesian formulation of physics-informed neural networks that enables automatic optimization of loss weights between PDE residuals, boundary conditions, and observational data. Unlike existing Bayesian PINN…

Computational Physics · Physics 2026-05-29 Krzysztof M. Graczyk , Kornel Witkowski

Physics-Informed Neural Networks (PINNs) encounter accuracy limitations when solving the Allen--Cahn (AC) and Cahn--Hilliard (CH) partial differential equations (PDEs). To overcome this, we employ a novel loss function, Residuals-weighted…

Numerical Analysis · Mathematics 2026-02-25 Guangtao Zhang , Jiani Lin , Qijia Zhai , Huiyu Yang , Xujun Chen , Ieng Tak Leong , Fang Zhu

The approximation power of general feedforward neural networks with piecewise linear activation functions is investigated. First, lower bounds on the size of a network are established in terms of the approximation error and network depth…

Machine Learning · Computer Science 2018-07-02 Mohammad Mehrabi , Aslan Tchamkerten , Mansoor I. Yousefi

The article discusses the development of various methods and techniques for initializing and training neural networks with a single hidden layer, as well as training a separable physics-informed neural network consisting of neural networks…

Numerical Analysis · Mathematics 2025-07-08 Vasiliy A. Es'kin , Alexey O. Malkhanov , Mikhail E. Smorkalov

The ability to accurately approximate trajectories of dynamical systems enables their analysis, prediction, and control. Neural network (NN)-based approximations have attracted significant interest due to fast evaluation with good accuracy…

Computational Physics · Physics 2024-01-11 Jochen Stiasny , Spyros Chatzivasileiadis

We consider two-grid mixed-finite element schemes for the spatial discretization of the incompressible Navier-Stokes equations. A standard mixed-finite element method is applied over the coarse grid to approximate the nonlinear…

Numerical Analysis · Mathematics 2016-12-23 Javier de Frutos , Bosco García-Archilla , Julia Novo

Various iterative reconstruction algorithms for inverse problems can be unfolded as neural networks. Empirically, this approach has often led to improved results, but theoretical guarantees are still scarce. While some progress on…

Statistics Theory · Mathematics 2021-08-16 Arash Behboodi , Holger Rauhut , Ekkehard Schnoor

This paper studies the approximation capacity of neural networks with an arbitrary activation function and with norm constraint on the weights. Upper and lower bounds on the approximation error of these networks are computed for smooth…

Numerical Analysis · Mathematics 2025-12-24 Francesco Paolo Maiale , Anastasiia Trofimova , Arturo De Marinis

Inverse problems in fluid dynamics are ubiquitous in science and engineering, with applications ranging from electronic cooling system design to ocean modeling. We propose a general and robust approach for solving inverse problems in the…

Numerical Analysis · Mathematics 2020-11-20 Tiffany Fan , Kailai Xu , Jay Pathak , Eric Darve

Physics-informed neural networks (PINNs) are successful machine-learning methods for the solution and identification of partial differential equations (PDEs). We employ PINNs for solving the Reynolds-averaged Navier$\unicode{x2013}$Stokes…

Fluid Dynamics · Physics 2022-07-20 Hamidreza Eivazi , Mojtaba Tahani , Philipp Schlatter , Ricardo Vinuesa
‹ Prev 1 3 4 5 6 7 10 Next ›