Local approximation of operators
Many current problems of interest such as deep learning, neural networks, inverse problems and solutions of partial differential equation can be expressed as the approximation of operators on compact sets. Concretely, we are given finitely many data that describe the operator and we wish to study the order of approximation that can be achieved by encoding/decoding of the data. The main problem in this task is the so-called curse of dimensionality, because the number of data and the dimensions of the underlying spaces, respectively, can be prohibitively large. In this article, the approximation orders of these approximation operators are studied with a particular emphasis to having efficient algorithms, precise constants in the error estimates and especially useful upper bounds. The article's theme should in particular contrasted to the classical questions of approximation theory where (nonlinear) functions are approximated, where in this paper we deal now with nonlinear operators and functionals. In this context, it is very relevant that its special usefulness also comes from the uniform error estimates that are important in practice, as compared to the standard estimates in Hilbert space norm which are good in theory, seen often in other contributions, but less useful in applications. A particular emphasis is placed on examples of operators defined on high-dimensional spheres.
- Approximation by spherical convolution operators
- Tensor-product approximation to operators and functions in high dimensions
- Some nonlinear problems are as easy as the approximation problem
- Error estimates for approximate operator inversion via kernel-based methods
- The adaption problem for approximating linear operators
- A generalized diffusion frame for parsimonious representation of functions on data defined manifolds
- A quadrature formula for diffusion polynomials corresponding to a generalized heat kernel
- An upper bound on Jacobi polynomials
- Analytic regularity and polynomial approximation of parametric and stochastic elliptic PDE's
- Approximate Quadrature Measures on Data-Defined Spaces
- Approximation properties of zonal function networks using scattered data on the sphere
- Approximation Theory and Harmonic Analysis on Spheres and Balls
- Concentration inequalities. A nonasymptotic theory of independence
- Deep vs. shallow networks: an approximation theory perspective
- Diffusion polynomial frames on metric measure spaces
- Exponential tractability of linear weighted tensor product problems in the worst-case setting for arbitrary linear functionals
- Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions
- scientific article; zbMATH DE number 2127848 (Why is no real title available?)
- scientific article; zbMATH DE number 5000378 (Why is no real title available?)
- scientific article; zbMATH DE number 4144656 (Why is no real title available?)
- scientific article; zbMATH DE number 3474264 (Why is no real title available?)
- scientific article; zbMATH DE number 3601500 (Why is no real title available?)
- scientific article; zbMATH DE number 503288 (Why is no real title available?)
- scientific article; zbMATH DE number 7626805 (Why is no real title available?)
- scientific article; zbMATH DE number 3254118 (Why is no real title available?)
- scientific article; zbMATH DE number 3108589 (Why is no real title available?)
- Localized summability kernels for Jacobi expansions
- Marcinkiewicz-Zygmund measures on manifolds
- Neural Networks for Functional Approximation and System Identification
- On a filter for exponentially localized kernels based on Jacobi polynomials
- On Some Extremal Functions and their Applications in the Theory of Analytic Functions of Several Complex Variables
- Optimal nonlinear approximation
- Some new characterizations of the Chebyshev polynomials
- Spherical Marcinkiewicz-Zygmund inequalities and positive quadrature
- The Random Feature Model for Input-Output Maps between Banach Spaces
- Tractability for Volterra problems of the second kind with convolution kernels
- Tractability of multivariate problems. Volume I: Linear information
- Weighted quadrature formulas and approximation by zonal function networks on the sphere
- Local principle of computation of the factor-norms of singular integral operators
- Local approximation by Beta operators
- Local approximations based on orthogonal differential operators
- scientific article; zbMATH DE number 5855096 (Why is no real title available?)
- scientific article; zbMATH DE number 1375527 (Why is no real title available?)
- Local sampling and approximation of operators with bandlimited Kohn-Nirenberg symbols
- scientific article; zbMATH DE number 5066357 (Why is no real title available?)
- Local operators and a characterization of the Volterra operator
- Is hyperinterpolation efficient in the approximation of singular and oscillatory functions?
- Local approximation of operators
- Transformers as neural operators for solutions of differential equations with finite regularity
- Nonlinear functional regression by functional deep neural network with kernel embedding
- Local approximation spaces
This page was built for publication: Local approximation of operators
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2689140)
