Optimality of 1-norm regularization among weighted 1-norms for sparse recovery: a case study on how to find optimal regularizations - Archive ouverte HAL
Communication Dans Un Congrès Année : 2018

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

Résumé

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.
Fichier principal
Vignette du fichier
case_study_optimal_reg_hal3.pdf (215.27 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01720871 , version 1 (01-03-2018)
hal-01720871 , version 2 (06-03-2018)
hal-01720871 , version 3 (18-05-2018)

Identifiants

Citer

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. 8th International Conference on New Computational Methods for Inverse Problems, May 2018, Paris, France. pp.conference 1, ⟨10.1088/1742-6596/1131/1/012009⟩. ⟨hal-01720871v3⟩
280 Consultations
195 Téléchargements

Altmetric

Partager

More