A theory of optimal convex regularization for low-dimensional recovery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Traonmilin, Yann, Gribonval, Rémi, Vaiter, Samuel
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911845296635904
author Traonmilin, Yann
Gribonval, Rémi
Vaiter, Samuel
author_facet Traonmilin, Yann
Gribonval, Rémi
Vaiter, Samuel
contents We consider the problem of recovering elements of a low-dimensional model from under-determined linear measurements. To perform recovery, we consider the minimization of a convex regularizer subject to a data fit constraint. Given a model, we ask ourselves what is the "best" convex regularizer to perform its recovery. To answer this question, we define an optimal regularizer as a function that maximizes a compliance measure with respect to the model. We introduce and study several notions of compliance. We give analytical expressions for compliance measures based on the best-known recovery guarantees with the restricted isometry property. These expressions permit to show the optimality of the ${\ell}$1-norm for sparse recovery and of the nuclear norm for low-rank matrix recovery for these compliance measures. We also investigate the construction of an optimal convex regularizer using the examples of sparsity in levels and of sparse plus low-rank models.
format Preprint
id arxiv_https___arxiv_org_abs_2112_03540
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle A theory of optimal convex regularization for low-dimensional recovery
Traonmilin, Yann
Gribonval, Rémi
Vaiter, Samuel
Signal Processing
We consider the problem of recovering elements of a low-dimensional model from under-determined linear measurements. To perform recovery, we consider the minimization of a convex regularizer subject to a data fit constraint. Given a model, we ask ourselves what is the "best" convex regularizer to perform its recovery. To answer this question, we define an optimal regularizer as a function that maximizes a compliance measure with respect to the model. We introduce and study several notions of compliance. We give analytical expressions for compliance measures based on the best-known recovery guarantees with the restricted isometry property. These expressions permit to show the optimality of the ${\ell}$1-norm for sparse recovery and of the nuclear norm for low-rank matrix recovery for these compliance measures. We also investigate the construction of an optimal convex regularizer using the examples of sparsity in levels and of sparse plus low-rank models.
title A theory of optimal convex regularization for low-dimensional recovery
topic Signal Processing
url https://arxiv.org/abs/2112.03540