l1Penalty for Ill-Posed Inverse Problems

DOI10.1080/03610920701826013MaRDI QIDQ3634545zbMATH OpenOpenAlexFDO

Authors Jean-Michel Loubes

Publication date 25 June 2009

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

Full work available at URL https://arxiv.org/abs/0709.2606

zbMATH Keywords

asymptotic statisticsinverse problemspenalized M-estimationsparsity

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Asymptotic properties of nonparametric inference (62G20) Numerical solution to inverse problems in abstract spaces (65J22)

Abstract: We tackle the problem of recovering an unknown signal observed in an ill-posed inverse problem framework. More precisely, we study a procedure commonly used in numerical analysis or image deblurring: minimizing an empirical loss function balanced by an $l^1$ penalty, acting as a sparsity constraint. We prove that, by choosing a proper loss function, this estimation technique enables to build an adaptive estimator, in the sense that it converges at the optimal rate of convergence without prior knowledge of the regularity of the true solution

Recommendations

• Adaptive complexity regularization for linear inverse problems
• \(\ell^{1}\) sparsity and applications in estimation
• Penalized estimators for non linear inverse problems
• On the role of sparsity in inverse problems
• scientific article; zbMATH DE number 2163517

Cites work

• Adaptive estimation with soft thresholding penalties
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• Consistency and rates of convergence of nonlinear Tikhonov regularization with random noise
• scientific article; zbMATH DE number 879844 (Why is no real title available?)
• scientific article; zbMATH DE number 936298 (Why is no real title available?)
• scientific article; zbMATH DE number 1420699 (Why is no real title available?)
• Nonparametric instrumental regression
• Oracle inequalities for inverse problems
• Regularization by projection with a posteriori discretization level choice for linear and nonlinear ill-posed problems
• Regularization methods for solving inverse problems
• Statistical Inverse Estimation in Hilbert Scales
• Tikhonov regularization anda posteriorirules for solving nonlinear ill posed problems
• Wavelets, approximation, and statistical applications

Cited in

(7)

• Adaptive complexity regularization for linear inverse problems
• Multidimensional hazard estimation under generalized censoring
• The springback penalty for robust signal recovery
• Local behavior of sparse analysis regularization: applications to risk estimation
• Optimal estimation of \(\ell_1\)-regularization prior from a regularized empirical Bayesian risk standpoint
• \(\ell^{1}\) sparsity and applications in estimation
• A new \(L\)-curve for ill-posed problems

This page was built for publication: l¹Penalty for Ill-Posed Inverse Problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3634545)