Low Complexity Regularizations of Inverse Problems

Abstract : This thesis is concerned with recovery guarantees and sensitivity analysis of variational regularization for noisy linear inverse problems. This is cast as a convex optimization problem by combining a data fidelity and a regularizing functional promoting solutions conforming to some notion of low complexity related to their non-smoothness points. Our approach, based on partial smoothness, handles a variety of regularizers including analysis/structured sparsity, antisparsity and low-rank structure. We first give an analysis of the noise robustness guarantees, both in terms of the distance of the recovered solutions to the original object, as well as the stability of the promoted model space. We then turn to sensivity analysis of these optimization problems to observation perturbations. With random observations, we build unbiased estimator of the risk which provides a parameter selection scheme.
Liste complète des métadonnées

Cited literature [209 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01026398
Contributor : Samuel Vaiter <>
Submitted on : Monday, July 21, 2014 - 3:27:54 PM
Last modification on : Wednesday, July 18, 2018 - 12:42:02 PM
Document(s) archivé(s) le : Monday, November 24, 2014 - 9:20:31 PM

Identifiers

  • HAL Id : tel-01026398, version 1

Collections

Citation

Samuel Vaiter. Low Complexity Regularizations of Inverse Problems. Information Theory [math.IT]. Université Paris Dauphine - Paris IX, 2014. English. 〈tel-01026398〉

Share

Metrics

Record views

671

Files downloads

481