Solution of linear ill-posed problems using overcomplete dictionaries

DOI10.1214/16-AOS1445zbMATH Open1346.62061arXiv1408.3386OpenAlexW2963208245MaRDI QIDQ309741FDOQ309741

Authors: Marianna Pensky 

Publication date: 7 September 2016

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: In the present paper we consider application of overcomplete dictionaries to solution of general ill-posed linear inverse problems. Construction of an adaptive optimal solution for such problems usually relies either on a singular value decomposition or representation of the solution via an orthonormal basis. The shortcoming of both approaches lies in the fact that, in many situations, neither the eigenbasis of the linear operator nor a standard orthonormal basis constitutes an appropriate collection of functions for sparse representation of the unknown function. In the context of regression problems, there have been an enormous amount of effort to recover an unknown function using an overcomplete dictionary. One of the most popular methods, Lasso, is based on minimizing the empirical likelihood and requires stringent assumptions on the dictionary, the, so called, compatibility conditions. While these conditions may be satisfied for the original dictionary functions, they usually do not hold for their images due to contraction imposed by the linear operator. In what follows, we bypass this difficulty by a novel approach which is based on inverting each of the dictionary functions and matching the resulting expansion to the true function, thus, avoiding unrealistic assumptions on the dictionary and using Lasso in a predictive setting. We examine both the white noise and the observational model formulations and also discuss how exact inverse images of the dictionary functions can be replaced by their approximate counterparts. Furthermore, we show how the suggested methodology can be extended to the problem of estimation of a mixing density in a continuous mixture. For all the situations listed above, we provide the oracle inequalities for the risk in a finite sample setting. Simulation studies confirm good computational properties of the Lasso-based technique.

Full work available at URL: https://arxiv.org/abs/1408.3386

Recommendations

• Solution of linear ill-posed problems using random dictionaries
• Solution of linear ill-posed problems by model selection and aggregation
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• Regularization of some linear ill-posed problems with discretized random noisy data
• scientific article; zbMATH DE number 2163517

zbMATH Keywords

Lassooracle inequalityadaptive estimationlinear inverse problems

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Bayesian problems; characterization of Bayes procedures (62C10)

Cites Work

• Statistics for high-dimensional data. Methods, theory and applications.
• Sharp oracle inequalities for aggregation of affine estimators
• Simultaneous analysis of Lasso and Dantzig selector
• Model Selection and Estimation in Regression with Grouped Variables
• Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition
• Sparsity oracle inequalities for the Lasso
• Title not available (Why is that?)
• Oracle inequalities and optimal inference under group sparsity
• On the prediction performance of the Lasso
• Adaptive demixing in Poisson mixture models
• Oracle inequalities for inverse problems
• Adaptive Laguerre density estimation for mixed Poisson models
• Nonparametric Estimation of a Mixing Density via the Kernel Method
• Risk hull method and regularization by projections of ill-posed inverse problems
• Deconvolution problems in nonparametric statistics
• SPADES and mixture models
• Thresholding estimators for linear inverse problems and deconvolutions
• Ridgelets: estimating with ridge functions
• Sparse model selection under heterogeneous noise: exact penalisation and data-driven thresholding
• Nonlinear estimation for linear inverse problems with error in the operator
• Title not available (Why is that?)
• Wavelet decomposition approaches to statistical inverse problems
• On inverse problems with unknown operators
• Adaptive Wavelet Galerkin Methods for Linear Inverse Problems
• On universal oracle inequalities related to high-dimensional linear models

Cited In (4)

• Estimation of a delta-contaminated density of a random intensity of Poisson data
• On the prediction loss of the Lasso in the partially labeled setting
• Solution of linear ill-posed problems using random dictionaries
• Solution of linear ill-posed problems by model selection and aggregation

This page was built for publication: Solution of linear ill-posed problems using overcomplete dictionaries

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q309741)