Concentration inequalities for cross-validation in scattered data approximation

DOI10.1016/j.jat.2022.105715OpenAlexW3199202651MaRDI QIDQ2120815

Felix Bartel, Ralf Hielscher

Publication date: 1 April 2022

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

Full work available at URL: https://arxiv.org/abs/2105.13790

zbMATH Keywords

model selectioncross-validationscattered data approximationconcentration inequalitiesparameter choice

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Nonparametric estimation (62G05) Hypothesis testing in multivariate analysis (62H15) Multidimensional problems (41A63) Spline approximation (41A15)

Related Items

Error guarantees for least squares approximation with noisy samples in domain adaptation

Uses Software

• Matlab
• gss
• NFFT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Efficient algorithms for robust generalized cross-validation spline smoothing
• Breaking the curse for uniform approximation in Hilbert spaces via Monte Carlo methods
• Fast cross-validation in harmonic approximation
• On the convergence of the quasioptimality criterion for (iterated) Tikhonov regularization
• Efficient computation for Whittaker-Henderson smoothing
• Asymptotic optimality of \(C_ L\) and generalized cross-validation in ridge regression with application to spline smoothing
• Laws of the iterated logarithm for order statistics of uniform spacings
• Generalizing the finite element method: Diffuse approximation and diffuse elements
• A distribution-free theory of nonparametric regression
• Smoothing inversion of Fourier series using generalized cross-validation
• Adaptive kernel methods using the balancing principle
• Manifold approximation by moving least-squares projection (MMLS)
• Fast generalized cross validation using Krylov subspace methods
• Regularization of statistical inverse problems and the Bakushinskiĭ veto
• Random ε-nets and embeddings in l^N_∞
• Robust generalized cross-validation for choosing the regularization parameter
• Support Vector Machines
• Regularization independent of the noise level: an analysis of quasi-optimality
• On the lengths of the pieces of a stick broken at random
• Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter
• Element‐free Galerkin methods
• The quasi-optimality criterion in the linear functional strategy
• 10.1162/jmlr.2003.3.4-5.621