Sampling discretization error of integral norms for function classes with small smoothness

DOI10.1016/J.JAT.2023.105913zbMATH Open1528.41069arXiv2203.07126OpenAlexW4377234276MaRDI QIDQ6165573FDOQ6165573

Authors: V. N. Temlyakov 

Publication date: 1 August 2023

Published in: Journal of Approximation Theory (Search for Journal in Brave)

Abstract: We consider infinitely dimensional classes of functions and instead of the relative error setting, which was used in previous papers on the integral norm discretization, we consider the absolute error setting. We demonstrate how known results from two areas of research -- supervised learning theory and numerical integration -- can be used in sampling discretization of the square norm on different function classes. We prove a general result, which shows that the sequence of entropy numbers of a function class in the uniform norm dominates, in a certain sense, the sequence of errors of sampling discretization of the square norm of this class. Then we use this result for establishing new error bounds for sampling discretization of the square norm on classes of multivariate functions with mixed smoothness.

Full work available at URL: https://arxiv.org/abs/2203.07126

Recommendations

• Some improved bounds in sampling discretization of integral norms
• Sampling discretization of integral norms
• Sampling discretization of integral norms and its application
• Sampling discretization of the uniform norm and applications
• Sampling discretization and related problems

zbMATH Keywords

learningnumerical integrationsampling discretization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Numerical integration (65D30) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Cites Work

• Hyperbolic cross approximation. Lecture notes given at the courses on constructive approximation and harmonic analysis, Barcelona, Spain, May 30 -- June 3, 2016
• On the mathematical foundations of learning
• Multivariate approximation
• A distribution-free theory of nonparametric regression
• Deterministic and stochastic error bounds in numerical analysis
• Greedy approximation with regard to non-greedy bases
• Entropy numbers, s-numbers, and eigenvalue problems
• CUBATURE FORMULAS FOR CLASSES OF FUNCTIONS WITH BOUNDED MIXED DIFFERENCE
• Quadrature and widths
• Integral norm discretization and related problems
• Function spaces with dominating mixed smoothness
• The Marcinkiewicz-type discretization theorems
• The Marcinkiewicz-type discretization theorems for the hyperbolic cross
• Sampling discretization and related problems
• Bounds on Kolmogorov widths and sampling recovery for classes with small mixed smoothness
• Sampling discretization error of integral norms for function classes

Cited In (2)

• Discretization error of irregular sampling approximations of stochastic integrals
• Sampling inequalities for infinitely smooth radial basis functions and its application to error estimates

This page was built for publication: Sampling discretization error of integral norms for function classes with small smoothness

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6165573)