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]
< Reduce
Signal et Communications [IRIT-SC]
Centre National de la Recherche Scientifique [CNRS]
Language
en
Document de travail - Pré-publication
English Abstract
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 ...Read more >
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.Read less <
English Keywords
off-the-grid sparse recovery
non-convex methods
over-parametrization
projected gradient descent
microscopy
ANR Project
Régularisation performante de problèmes inverses en grande dimension pour le traitement de données - ANR-20-CE40-0001
Origin
Hal imported