Inverse learning in Hilbert scales

DOI10.1007/S10994-022-06284-8MaRDI QIDQ6134325zbMATH OpenOpenAlexFDO

Authors Abhishake Rastogi, Peter Mathé

Publication date 22 August 2023

Published in Machine Learning (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2002.10208

zbMATH Keywords

reproducing kernel Hilbert spaceminimax convergence ratesHilbert scalesstatistical inverse problemspectral regularization

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Learning and adaptive systems in artificial intelligence (68T05) Numerical solutions to equations with nonlinear operators (65J15) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Numerical solution to inverse problems in abstract spaces (65J22)

Abstract: We study the linear ill-posed inverse problem with noisy data in the statistical learning setting. Approximate reconstructions from random noisy data are sought with general regularization schemes in Hilbert scale. We discuss the rates of convergence for the regularized solution under the prior assumptions and a certain link condition. We express the error in terms of certain distance functions. For regression functions with smoothness given in terms of source conditions the error bound can then be explicitly established.

Recommendations

• Nonlinear Tikhonov regularization in Hilbert scales for inverse learning
• Tikhonov regularization with oversmoothing penalty for nonlinear statistical inverse problems
• Statistical Inverse Estimation in Hilbert Scales
• Interpolation in variable Hilbert scales with application to inverse problems
• Optimal rates for regularization of statistical inverse learning problems

Cites work

• scientific article; zbMATH DE number 4011018 (Why is no real title available?)
• scientific article; zbMATH DE number 936298 (Why is no real title available?)
• scientific article; zbMATH DE number 967931 (Why is no real title available?)
• A priori parameter choice in Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems
• An a Posteriori Parameter Choice for Tikhonov Regularization in Hilbert Scales Leading to Optimal Convergence Rates
• Analysis of Profile Functions for General Linear Regularization Methods
• Approximate source conditions in Tikhonov–Phillips regularization and consequences for inverse problems with multiplication operators
• Balancing principle in supervised learning for a general regularization scheme
• Bayesian inverse problems with non-commuting operators
• Bayesian linear inverse problems in regularity scales
• Convergence analysis of Tikhonov regularization for non-linear statistical inverse problems
• Convergence rates for Tikhonov regularization from different kinds of smoothness conditions
• Designing truncated priors for direct and inverse Bayesian problems
• Discrepancy principle for statistical inverse problems with application to conjugate gradient iteration
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Error Estimates for Regularization Methods in Hilbert Scales
• Error bounds for regularization methods in Hilbert scales by using operator monotonicity
• Error bounds for tikhonov regularization in hilbert scales
• Geometry of linear ill-posed problems in variable Hilbert scales
• Interpolation in variable Hilbert scales with application to inverse problems
• Kernel regression, minimax rates and effective dimensionality: beyond the regular case
• Learning theory of distributed spectral algorithms
• Multiple operator integrals in perturbation theory
• On Learning Vector-Valued Functions
• On Morozov's method for Tikhonov regularization as an optimal order yielding algorithm
• On regularization algorithms in learning theory
• Optimal order results for a class of regularization methods using unbounded operators
• Optimal rates for regularization of statistical inverse learning problems
• Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
• Optimal rates for the regularized least-squares algorithm
• Oracle-type posterior contraction rates in Bayesian inverse problems
• Regularization in Hilbert scales under general smoothing conditions
• Regularization theory for ill-posed problems. Selected topics
• Theory of Reproducing Kernels
• Tikhonov Regularization for Finitely and Infinitely Smoothing Operators
• Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems in Hilbert scales

Cited in

(3)

• Regularization of statistical inverse problems and the Bakushinskiĭ veto
• Nonlinear Tikhonov regularization in Hilbert scales for inverse learning
• Tikhonov Regularization with Oversmoothing Penalty: Error Bounds in Terms of Distance Functions

This page was built for publication: Inverse learning in Hilbert scales

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6134325)