Pré-Publication, Document De Travail Année : 2025

From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent

Résumé

We consider the problem of recovering an unknown low-dimensional vector from noisy, underdetermined observations. We focus on the Generalized Projected Gradient Descent (GPGD) framework, which unifies traditional sparse recovery methods and modern approaches using learned deep projective priors. We extend previous convergence results to robustness to model and projection errors. We use these theoretical results to explore ways to better control stability and robustness constants. To reduce recovery errors due to measurement noise, we consider generalized back-projection strategies to adapt GPGD to structured noise, such as sparse outliers. To improve the stability of GPGD, we propose a normalized idempotent regularization for the learning of deep projective priors. We provide numerical experiments in the context of sparse recovery and image inverse problems, highlighting the trade-offs between identifiability and stability that can be achieved with such methods.

Fichier principal
Vignette du fichier
stable_recovery.pdf (11.65 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05401157 , version 1 (05-12-2025)

Licence

Identifiants

Citer

Ali Joundi, Yann Traonmilin, Jean-François Aujol. From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent. 2025. ⟨hal-05401157⟩
199 Consultations
79 Téléchargements

Altmetric

Partager

  • More