Estimation of off-the grid sparse spikes with over-parametrized projected gradient descent: theory and application
DOI10.1088/1361-6420/ad33e4zbMATH Open1541.94009MaRDI QIDQ6557666
Pierre-Jean Bénard, Jean-François Aujol, Emmanuel Soubies, Yann Traonmilin
Publication date: 18 June 2024
Published in: Inverse Problems (Search for Journal in Brave)
microscopyover-parametrizationprojected gradient descentnon-convex methodsoff-the-grid sparse recovery
Classification and discrimination; cluster analysis (statistical aspects) (62H30) Convex programming (90C25) Nonconvex programming, global optimization (90C26) Numerical optimization and variational techniques (65K10) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Cites Work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- The restricted isometry property and its implications for compressed sensing
- Sparse optimization on measures with over-parameterized gradient descent
- Adaptive restart for accelerated gradient schemes
- When does OMP achieve exact recovery with continuous dictionaries?
- Compressive statistical learning with random feature moments
- Statistical learning guarantees for compressive clustering and compressive mixture modeling
- Exact Solutions to Super Resolution on Semi-Algebraic Domains in Higher Dimensions
- Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
- A Primal-Dual Proximal Algorithm for Sparse Template-Based Adaptive Filtering: Application to Seismic Multiple Removal
- Spectral Compressed Sensing via Projected Gradient Descent
- The basins of attraction of the global minimizers of the non-convex sparse spike estimation problem
- The sliding Frank–Wolfe algorithm and its application to super-resolution microscopy
- Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
- Sketching for large-scale learning of mixture models
- Gershgorin's Theorem and the Zeros of Polynomials
- Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems
- Towards a Mathematical Theory of Super‐resolution
- Blind inverse problems with isolated spikes
- The basins of attraction of the global minimizers of non-convex inverse problems with low-dimensional models in infinite dimension
Related Items (1)
This page was built for publication: Estimation of off-the grid sparse spikes with over-parametrized projected gradient descent: theory and application
