Inverse learning in Hilbert scales

DOI10.1007/S10994-022-06284-8arXiv2002.10208OpenAlexW3006775030MaRDI QIDQ6134325FDOQ6134325

Authors: Abhishake Rastogi, Peter Mathé 

Publication date: 22 August 2023

Published in: Machine Learning (Search for Journal in Brave)

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.

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

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

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)

Cites Work

• On Learning Vector-Valued Functions
• Theory of Reproducing Kernels
• Title not available (Why is that?)
• Optimal rates for the regularized least-squares algorithm
• Oracle-type posterior contraction rates in Bayesian inverse problems
• Discrepancy principle for statistical inverse problems with application to conjugate gradient iteration
• Regularization theory for ill-posed problems. Selected topics
• Geometry of linear ill-posed problems in variable Hilbert scales
• Title not available (Why is that?)
• Multiple operator integrals in perturbation theory
• Tikhonov Regularization for Finitely and Infinitely Smoothing Operators
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• On regularization algorithms in learning theory
• Title not available (Why is that?)
• Approximate source conditions in Tikhonov–Phillips regularization and consequences for inverse problems with multiplication operators
• Regularization in Hilbert scales under general smoothing conditions
• Interpolation in variable Hilbert scales with application to inverse problems
• Error bounds for regularization methods in Hilbert scales by using operator monotonicity
• Analysis of Profile Functions for General Linear Regularization Methods
• An a Posteriori Parameter Choice for Tikhonov Regularization in Hilbert Scales Leading to Optimal Convergence Rates
• Error bounds for tikhonov regularization in hilbert scales
• Error Estimates for Regularization Methods in Hilbert Scales
• Optimal rates for regularization of statistical inverse learning problems
• Convergence rates for Tikhonov regularization from different kinds of smoothness conditions
• On Morozov's method for Tikhonov regularization as an optimal order yielding algorithm
• A priori parameter choice in Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems
• Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
• Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems in Hilbert scales
• Learning theory of distributed spectral algorithms
• Balancing principle in supervised learning for a general regularization scheme
• Optimal order results for a class of regularization methods using unbounded operators
• Bayesian inverse problems with non-commuting operators
• Bayesian linear inverse problems in regularity scales
• Kernel regression, minimax rates and effective dimensionality: beyond the regular case
• Designing truncated priors for direct and inverse Bayesian problems
• Convergence analysis of Tikhonov regularization for non-linear statistical inverse problems

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)