Operator learning at machine precision

DOI10.1016/J.JCP.2026.115240MaRDI QIDQ7395914zbMATH OpenFDO

Authors Aras Bacho, Xianjin Yang, Théo Bourdais, Edoardo Calvello, Matthieu Darcy, Alexander W. Hsu, Bamdad Hosseini, Houman Owhadi

Publication date 2026

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCP.2026.115240

Mathematics Subject Classification ID

Partial differential equations (35-XX) Numerical analysis (65-XX)

Cites work

• A kernel framework for learning differential equations and their solution operators
• A Levenberg-Marquardt method for nonsmooth regularized least squares
• Bayesian calibration of computer models. (With discussion)
• Compression, inversion, and approximate PCA of dense kernel matrices at near-linear computational complexity
• Computational graph completion
• Continuum attention for neural operators
• Data-driven identification of parametric partial differential equations
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• Do ideas have shape? Idea registration as the continuous limit of artificial neural networks
• Estimates on the generalization error of physics-informed neural networks for approximating a class of inverse problems for PDEs
• Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
• Fredholm neural networks
• scientific article; zbMATH DE number 3933857 (Why is no real title available?)
• scientific article; zbMATH DE number 635667 (Why is no real title available?)
• scientific article; zbMATH DE number 5060482 (Why is no real title available?)
• Inexact Newton Methods
• Kernel flows: from learning kernels from data into the abyss
• Kernel methods are competitive for operator learning
• Model order reduction: Theory, research aspects and applications. Selected papers based on the presentations at the workshop `Model order reduction, coupled problems and optimization', Leiden, The Netherlands, September 19--23, 2005.
• Multigrid with Rough Coefficients and Multiresolution Operator Decomposition from Hierarchical Information Games
• Nested kriging predictions for datasets with a large number of observations
• Newton-Kantorovich method and its global convergence
• Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
• Numerical homogenization beyond scale separation
• On optimization techniques for solving nonlinear inverse problems
• Operator learning with Gaussian processes
• Operator-adapted wavelets, fast solvers, and numerical homogenization. From a game theoretic approach to numerical approximation and algorithm design
• Operator-valued kernels for learning from functional response data
• Quasi-Newton methods for large-scale electromagnetic inverse problems
• Randomly pivoted Cholesky: practical approximation of a kernel matrix with few entry evaluations
• RandONets: shallow networks with random projections for learning linear and nonlinear operators
• Scientific machine learning through physics-informed neural networks: where we are and what's next
• Solving and learning nonlinear PDEs with Gaussian processes
• Sparse Cholesky Factorization by Kullback--Leibler Minimization
• Sparse Cholesky factorization for solving nonlinear PDEs via Gaussian processes
• Sparse Compression of Expected Solution Operators
• Sparse Recovery of Elliptic Solvers from Matrix-Vector Products
• The Levenberg-Marquardt method: an overview of modern convergence theories and more
• The Random Feature Model for Input-Output Maps between Banach Spaces
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations

This page was built for publication: Operator learning at machine precision

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7395914)