Kernel methods are competitive for operator learning (Q6202132)

scientific article; zbMATH DE number 7807976

Language	Label	Description	Also known as
English	Kernel methods are competitive for operator learning	scientific article; zbMATH DE number 7807976

Statements

instance of

scholarly article

0 references

title

Kernel methods are competitive for operator learning (English)

0 references

0 references

0 references

0 references

0 references

Journal of Computational Physics

0 references

publication date

21 February 2024

0 references

full work available at URL

https://arxiv.org/abs/2304.13202

0 references

zbMATH Keywords

operator learning

0 references

optimal recovery

0 references

kernel methods

0 references

Gaussian processes

0 references

functional regression

0 references

partial differential equations

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Numerical homogenization beyond scale separation

0 references

Kernels for Vector-Valued Functions: A Review

0 references

An extension of a bound for functions in Sobolev spaces, with applications to \((m, s)\)-spline interpolation and smoothing

0 references

ON THE OPTIMAL POLYNOMIAL APPROXIMATION OF STOCHASTIC PDES BY GALERKIN AND COLLOCATION METHODS

0 references

Q4449265

0 references

Model reduction and neural networks for parametric PDEs

0 references

Solving and learning nonlinear PDEs with Gaussian processes

0 references

Consistency of empirical Bayes and kernel flow for hierarchical parameter estimation

0 references

Sparse adaptive Taylor approximation algorithms for parametric and stochastic elliptic PDEs

0 references

High-dimensional adaptive sparse polynomial interpolation and applications to parametric PDEs

0 references

Approximation of high-dimensional parametric PDEs

0 references

BCR-net: A neural network based on the nonstandard wavelet form

0 references

A multiscale neural network based on hierarchical nested bases

0 references

A Multiscale Neural Network Based on Hierarchical Matrices

0 references

Sparse Compression of Expected Solution Operators

0 references

\(FE^2\) multiscale approach for modelling the elastoviscoplastic behaviour of long fibre SiC/Ti composite materials

0 references

Computational plasticity for composite structures based on mathematical homogenization: Theory and practice

0 references

Stochastic finite element methods for partial differential equations with random input data

0 references

Learning dynamical systems from data: a simple cross-validation perspective. I: Parametric kernel flows

0 references

Non-intrusive reduced order modeling of nonlinear problems using neural networks

0 references

Certified Reduced Basis Methods for Parametrized Partial Differential Equations

0 references

Iterated Kalman methodology for inverse problems

0 references

Q2810788

0 references

Bayesian Calibration of Computer Models

0 references

Solving parametric PDE problems with artificial neural networks

0 references

SwitchNet: A Neural Network Model for Forward and Inverse Scattering Problems

0 references

A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data

0 references

A priori convergence theory for reduced-basis approximations of single-parameter elliptic partial differential equations

0 references

Localization of elliptic multiscale problems

0 references

A Stochastic Newton MCMC Method for Large-Scale Statistical Inverse Problems with Application to Seismic Inversion

0 references

An Anisotropic Sparse Grid Stochastic Collocation Method for Partial Differential Equations with Random Input Data

0 references

A Sparse Grid Stochastic Collocation Method for Partial Differential Equations with Random Input Data

0 references

Bayesian Numerical Homogenization

0 references

Multigrid with Rough Coefficients and Multiresolution Operator Decomposition from Hierarchical Information Games

0 references

Computational graph completion

0 references

Do ideas have shape? Idea registration as the continuous limit of artificial neural networks

0 references

Operator-Adapted Wavelets, Fast Solvers, and Numerical Homogenization

0 references

Kernel flows: from learning kernels from data into the abyss

0 references

Metric-based upscaling

0 references

Gamblets for opening the complexity-bottleneck of implicit schemes for hyperbolic and parabolic ODEs/PDEs with rough coefficients

0 references

Q5396710

0 references

Q3394879

0 references

Sparse Cholesky Factorization by Kullback--Leibler Minimization

0 references

Compression, inversion, and approximate PCA of dense kernel matrices at near-linear computational complexity

0 references

Q3148817

0 references

Improved architectures and training algorithms for deep operator networks

0 references

Q5198904

0 references

Local error estimates for radial basis function interpolation of scattered data

0 references

Q3583848

0 references

The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations

0 references

Efficient stochastic Galerkin methods for random diffusion equations

0 references

Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification

0 references

Identifiers

arXiv ID

2304.13202

0 references

DOI

10.1016/j.jcp.2023.112549

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:6202132