Optimality of 1-norm regularization among weighted 1-norms for sparse recovery: a case study on how to find optimal regularizations

Abstract : The 1-norm was proven to be a good convex regularizer for the recovery of sparse vectors from under-determined linear measurements. It has been shown that with an appropriate measurement operator, a number of measurements of the order of the sparsity of the signal (up to log factors) is sufficient for stable and robust recovery. More recently, it has been shown that such recovery results can be generalized to more general low-dimensional model sets and (convex) regularizers. These results lead to the following question: to recover a given low-dimensional model set from linear measurements, what is the " best " convex regularizer? To approach this problem, we propose a general framework to define several notions of " best regularizer " with respect to a low-dimensional model. We show in the minimal case of sparse recovery in dimension 3 that the 1-norm is optimal for these notions. However, generalization of such results to the n-dimensional case seems out of reach. To tackle this problem, we propose looser notions of best regularizer and show that the 1-norm is optimal among weighted 1-norms for sparse recovery within this framework.
Type de document :
Pré-publication, Document de travail
2018
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01720871
Contributeur : Yann Traonmilin <>
Soumis le : vendredi 18 mai 2018 - 13:43:25
Dernière modification le : mercredi 18 juillet 2018 - 12:42:02
Document(s) archivé(s) le : mardi 25 septembre 2018 - 13:04:45

Fichiers

case_study_optimal_reg_hal3.pd...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01720871, version 3
  • ARXIV : 1803.00773

Collections

Citation

Yann Traonmilin, Samuel Vaiter. Optimality of 1-norm regularization among weighted 1-norms for sparse recovery: a case study on how to find optimal regularizations. 2018. 〈hal-01720871v3〉

Partager

Métriques

Consultations de la notice

74

Téléchargements de fichiers

31