Adaptive Gaussian inverse regression with partially unknown operator

DOI10.1080/03610926.2012.731548zbMATH Open1347.62056arXiv1204.1226OpenAlexW2049681635MaRDI QIDQ4929192FDOQ4929192

Authors: Jan Johannes, Maik Schwarz 

Publication date: 13 June 2013

Published in: Communications in Statistics: Theory and Methods (Search for Journal in Brave)

Abstract: This work deals with the ill-posed inverse problem of reconstructing a function $f$ given implicitly as the solution of $g=Af$, where $A$ is a compact linear operator with unknown singular values and known eigenfunctions. We observe the function $g$ and the singular values of the operator subject to Gaussian white noise with respective noise levels $varepsilon$ and $sigma$. We develop a minimax theory in terms of both noise levels and propose an orthogonal series estimator attaining the minimax rates. This estimator requires the optimal choice of a dimension parameter depending on certain characteristics of $f$ and $A$. This work addresses the fully data-driven choice of the dimension parameter combining model selection with Lepski's method. We show that the fully data-driven estimator preserves minimax optimality over a wide range of classes for $f$ and $A$ and noise levels $varepsilon$ and $sigma$. The results are illustrated considering Sobolev spaces and mildly and severely ill-posed inverse problems.

Full work available at URL: https://arxiv.org/abs/1204.1226

Recommendations

• Adaptive estimation for inverse problems with noisy operators
• Empirical risk minimization in inverse problems
• Oracle inequalities for inverse problems
• On inverse problems with unknown operators
• Rate optimal estimation of quadratic functionals in inverse problems with partially unknown operator and application to testing problems

zbMATH Keywords

model selectionSobolev spacesLepski's methodminimax theoryadaptive nonparametric estimationGaussian sequence space modelmildly and severely ill-posed inverse problems

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric regression and quantile regression (62G08) Minimax procedures in statistical decision theory (62C20)

Cites Work

• Deconvolving kernel density estimators
• On the optimal rates of convergence for nonparametric deconvolution problems
• Risk bounds for model selection via penalization
• Title not available (Why is that?)
• Oracle inequalities for inverse problems
• Bandwidth selection in kernel density estimation: oracle inequalities and adaptive minimax optimality
• Nonlinear estimation for linear inverse problems with error in the operator
• On inverse problems with unknown operators
• Speed of estimation in positron emission tomography and related inverse problems
• On the effect of estimating the error density in nonparametric deconvolution
• Statistical Inverse Estimation in Hilbert Scales
• Optimal discretization of inverse problems in Hilbert scales. Regularization and self-regulari\-za\-tion of projection methods
• Nonparametric quasi-maximum likelihood estimation for Gaussian locally stationary processes
• Adaptive estimation for inverse problems with noisy operators
• On optimal solutions of the deconvolution problem

Cited In (9)

• Adaptive estimation for inverse problems with noisy operators
• Estimation of convolution in the model with noise
• On inverse problems with unknown operators
• Deep learning for inverse problems with unknown operator
• Nonparametric intensity estimation from noisy observations of a Poisson process under unknown error distribution
• An adaptive ANOVA-based PCKF for high-dimensional nonlinear inverse modeling
• Adaptive estimation for an inverse regression model with unknown operator
• Minimax goodness-of-fit testing in ill-posed inverse problems with partially unknown operators
• Rate optimal estimation of quadratic functionals in inverse problems with partially unknown operator and application to testing problems

This page was built for publication: Adaptive Gaussian inverse regression with partially unknown operator

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4929192)