SPARSE REPRESENTATIONS WITH DATA FIDELITY TERM VIA AN ITERATIVELY REWEIGHTED LEAST SQUARES ALGORITHM
- Los Alamos National Laboratory
Basis Pursuit and Basis Pursuit Denoising, well established techniques for computing sparse representations, minimize an {ell}{sup 2} data fidelity term subject to an {ell}{sup 1} sparsity constraint or regularization term on the solution by mapping the problem to a linear or quadratic program. Basis Pursuit Denoising with an {ell}{sup 1} data fidelity term has recently been proposed, also implemented via a mapping to a linear program. They introduce an alternative approach via an iteratively Reweighted Least Squares algorithm, providing greater flexibility in the choice of data fidelity term norm, and computational advantages in certain circumstances.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- AC52-06NA25396
- OSTI ID:
- 1000493
- Report Number(s):
- LA-UR-07-0078; TRN: US201101%%596
- Country of Publication:
- United States
- Language:
- English
Similar Records
Sparsely corrupted stimulated scattering signals recovery by iterative reweighted continuous basis pursuit
Improving IMRT delivery efficiency with reweighted L1-minimization for inverse planning
A mixed $\ell_1$ regularization approach for sparse simultaneous approximation of parameterized PDEs
Journal Article
·
Thu Aug 15 00:00:00 EDT 2013
· Review of Scientific Instruments
·
OSTI ID:1000493
Improving IMRT delivery efficiency with reweighted L1-minimization for inverse planning
Journal Article
·
Mon Jul 15 00:00:00 EDT 2013
· Medical Physics
·
OSTI ID:1000493
+5 more
A mixed $\ell_1$ regularization approach for sparse simultaneous approximation of parameterized PDEs
Journal Article
·
Thu Jun 27 00:00:00 EDT 2019
· Mathematical Modelling and Numerical Analysis
·
OSTI ID:1000493