Estimation of off-the-grid sparse spikes with over-parametrized projected gradient descent: theory and application
SOUBIES, Emmanuel
Signal et Communications [IRIT-SC]
Centre National de la Recherche Scientifique [CNRS]
< Réduire
Signal et Communications [IRIT-SC]
Centre National de la Recherche Scientifique [CNRS]
Langue
en
Document de travail - Pré-publication
Résumé en anglais
In this article, we study the problem of recovering sparse spikes with overparametrized projected descent. We first provide a theoretical study of approximate recovery with our chosen initialization method: Continuous ...Lire la suite >
In this article, we study the problem of recovering sparse spikes with overparametrized projected descent. We first provide a theoretical study of approximate recovery with our chosen initialization method: Continuous Orthogonal Matching Pursuit without Sliding. Then we study the effect of over-parametrization on the gradient descent which highlights the benefits of the projection step. Finally, we show the improved calculation times of our algorithm compared to state-of-the-art modelbased methods on realistic simulated microscopy data.< Réduire
Mots clés en anglais
off-the-grid sparse recovery
non-convex methods
over-parametrization
projected gradient descent
microscopy
Project ANR
Régularisation performante de problèmes inverses en grande dimension pour le traitement de données - ANR-20-CE40-0001
Origine
Importé de halUnités de recherche