Fast off-the-grid sparse recovery with over-parametrized projected gradient descent
Language
en
Communication dans un congrès
This item was published in
2022 30th European Signal Processing Conference (EUSIPCO), 2022, Belgrade (Serbia).
English Abstract
We consider the problem of recovering off-the-grid spikes from Fourier measurements. Successful methods such as sliding Frank-Wolfe and continuous orthogonal matching pursuit (OMP) iteratively add spikes to the solution ...Read more >
We consider the problem of recovering off-the-grid spikes from Fourier measurements. Successful methods such as sliding Frank-Wolfe and continuous orthogonal matching pursuit (OMP) iteratively add spikes to the solution then perform a costly (when the number of spikes is large) descent on all parameters at each iteration. In 2D, it was shown that performing a projected gradient descent (PGD) from a gridded over-parametrized initialization was faster than continuous orthogonal matching pursuit. In this paper, we propose an off-the-grid over-parametrized initialization of the PGD based on OMP that permits to fully avoid grids and gives faster results in 3D.Read less <
English Keywords
spike super-resolution
non-convex optimization
over-parametrization
projected gradient descent
continuous orthogonal matching pursuit
ANR Project
Régularisation performante de problèmes inverses en grande dimension pour le traitement de données - ANR-20-CE40-0001
Origin
Hal imported