English
Related papers

Related papers: Model Reduction and Neural Networks for Parametric…

200 papers

We present two effective methods for solving high-dimensional partial differential equations (PDE) based on randomized neural networks. Motivated by the universal approximation property of this type of networks, both methods extend the…

Numerical Analysis · Mathematics 2023-09-14 Yiran Wang , Suchuan Dong

We study the approximation rates of a class of deep neural network approximations of operators which arise as data-to-solution maps $\mathcal{S}$ of linear elliptic partial differential equations (PDEs), and act between pairs $X,Y$ of…

Numerical Analysis · Mathematics 2025-12-22 Carlo Marcati , Christoph Schwab

The numerical solution of high dimensional partial differential equations (PDEs) is severely constrained by the curse of dimensionality (CoD), rendering classical grid--based methods impractical beyond a few dimensions. In recent years,…

Numerical Analysis · Mathematics 2026-01-27 Wenzhong Zhang , Zheyuan Hu , Wei Cai , George EM Karniadakis

Implicit Neural Representations (INRs) have emerged as a powerful tool for geometric representation, yet their suitability for physics-based simulation remains underexplored. While metrics like Hausdorff distance quantify surface…

Computational Engineering, Finance, and Science · Computer Science 2026-02-03 Samundra Karki , Adarsh Krishnamurthy , Baskar Ganapathysubramanian

Reduced model spaces, such as reduced basis and polynomial chaos, are linear spaces $V_n$ of finite dimension $n$ which are designed for the efficient approximation of families parametrized PDEs in a Hilbert space $V$. The manifold…

Numerical Analysis · Mathematics 2020-08-04 Albert Cohen , Wolfgang Dahmen , Ron DeVore , Jalal Fadili , Olga Mula , James Nichols

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Machine Learning · Computer Science 2025-09-16 Pedro Savarese

There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive…

Machine Learning · Computer Science 2019-10-29 Joshua Hanson , Maxim Raginsky

We propose new machine learning schemes for solving high dimensional nonlinear partial differential equations (PDEs). Relying on the classical backward stochastic differential equation (BSDE) representation of PDEs, our algorithms estimate…

Probability · Mathematics 2020-06-08 Côme Huré , Huyên Pham , Xavier Warin

Projection-based model reduction has become a popular approach to reduce the cost associated with integrating large-scale dynamical systems so they can be used in many-query settings such as optimization and uncertainty quantification. For…

Numerical Analysis · Mathematics 2020-08-26 Han Gao , Jian-Xun Wang , Matthew J. Zahr

We study the computational complexity of (deterministic or randomized) algorithms based on point samples for approximating or integrating functions that can be well approximated by neural networks. Such algorithms (most prominently…

Machine Learning · Computer Science 2021-04-08 Philipp Grohs , Felix Voigtlaender

We propose a neural network-based algorithm for solving forward and inverse problems for partial differential equations in unsupervised fashion. The solution is approximated by a deep neural network which is the minimizer of a cost…

Machine Learning · Computer Science 2019-04-12 Leah Bar , Nir Sochen

We develop several deep learning algorithms for approximating families of parametric PDE solutions. The proposed algorithms approximate solutions together with their gradients, which in the context of mathematical finance means that the…

Computational Finance · Quantitative Finance 2022-01-19 Marc Sabate Vidales , David Siska , Lukasz Szpruch

Ordinary and partial differential equations (ODEs/PDEs) play a paramount role in analyzing and simulating complex dynamic processes across all corners of science and engineering. In recent years machine learning tools are aspiring to…

Machine Learning · Computer Science 2021-06-11 Sifan Wang , Paris Perdikaris

This paper addresses the problem of modeling and estimating dynamic multi-valued mappings. While most mathematical models provide a unique solution for a given input, real-world applications often lack deterministic solutions. In such…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Geng Li , Di Qiu , Lok Ming Lui

We study the derivative-informed learning of nonlinear operators between infinite-dimensional separable Hilbert spaces by neural networks. Such operators can arise from the solution of partial differential equations (PDEs), and are used in…

Numerical Analysis · Mathematics 2025-04-14 Dingcheng Luo , Thomas O'Leary-Roseberry , Peng Chen , Omar Ghattas

Finding parameters in a deep neural network (NN) that fit training data is a nonconvex optimization problem, but a basic first-order optimization method (gradient descent) finds a global optimizer with perfect fit (zero-loss) in many…

Machine Learning · Computer Science 2025-03-07 Zhiyan Ding , Shi Chen , Qin Li , Stephen Wright

Within the framework of parameter dependent PDEs, we develop a constructive approach based on Deep Neural Networks for the efficient approximation of the parameter-to-solution map. The research is motivated by the limitations and drawbacks…

Numerical Analysis · Mathematics 2022-12-16 Nicola R. Franco , Andrea Manzoni , Paolo Zunino

We introduce the concept of data-driven finite element methods. These are finite-element discretizations of partial differential equations (PDEs) that resolve quantities of interest with striking accuracy, regardless of the underlying mesh…

Numerical Analysis · Mathematics 2022-11-15 Ignacio Brevis , Ignacio Muga , Kristoffer G. van der Zee

Parametrized families of PDEs arise in various contexts such as inverse problems, control and optimization, risk assessment, and uncertainty quantification. In most of these applications, the number of parameters is large or perhaps even…

Analysis of PDEs · Mathematics 2015-03-04 Albert Cohen , Ronald Devore

The Universal Approximation Theorem posits that neural networks can theoretically possess unlimited approximation capacity with a suitable activation function and a freely chosen or trained set of parameters. However, a more practical…

Machine Learning · Computer Science 2024-09-26 Li Liu , Tengchao Yu , Heng Yong