\(L_2\)-norm sampling discretization and recovery of functions from RKHS with finite trace

DOI10.1007/s43670-021-00013-3zbMath1506.41015arXiv2009.11940OpenAlexW3216643960MaRDI QIDQ2059812

Moritz Moeller, Tino Ullrich

Publication date: 14 December 2021

Published in: Sampling Theory, Signal Processing, and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2009.11940

zbMATH Keywords

discretizationrandom samplingleast squares approximationMarcinkiewicz-Zygmund inequalitiesspectral norm concentration

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Asymptotic approximations, asymptotic expansions (steepest descent, etc.) (41A60) Multidimensional problems (41A63) Rate of convergence, degree of approximation (41A25) Sampling theory in information and communication theory (94A20)

Related Items

Sampling discretization and related problems, A new upper bound for sampling numbers, A Note on Sampling Recovery of Multivariate Functions in the Uniform Norm, Weighted random sampling and reconstruction in general multivariate trigonometric polynomial spaces, Constructive subsampling of finite frames with applications in optimal function recovery, Random sampling over locally compact abelian groups and inversion of the Radon transform, A sharp upper bound for sampling numbers in \(L_2\), Error guarantees for least squares approximation with noisy samples in domain adaptation, On the reconstruction of functions from values at subsampled quadrature points, Worst-case recovery guarantees for least squares approximation using random samples, Interpretable Approximation of High-Dimensional Data

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs
• Sums of random Hermitian matrices and an inequality by Rudelson
• User-friendly tail bounds for sums of random matrices
• Tractability of multivariate problems. Volume III: Standard information for operators
• Sampling, Marcinkiewicz-Zygmund inequalities, approximation, and quadrature rules
• The entropy in learning theory. Error estimates
• On singular values of matrices with independent rows
• Random vectors in the isotropic position
• The Marcinkiewicz-type discretization theorems
• Function values are enough for \(L_2\)-approximation. II
• Hyperbolic cross approximation. Lecture notes given at the courses on constructive approximation and harmonic analysis, Barcelona, Spain, May 30 -- June 3, 2016
• On optimal recovery in \(L_2\)
• On the worst-case error of least squares algorithms for \(L_2\)-approximation with high probability
• Worst-case recovery guarantees for least squares approximation using random samples
• Some nonlinear problems are as easy as the approximation problem
• Sampling discretization error of integral norms for function classes
• Optimal Constants in Khintchine Type Inequalities for Fermions, Rademachers and q-Gaussian Operators
• Learning Theory
• Support Vector Machines
• LSQR: An Algorithm for Sparse Linear Equations and Sparse Least Squares
• Optimal weighted least-squares methods
• Operator Khintchine inequality in non-commutative probability
• On the power of standard information for weighted approximation