SPARSE REPRESENTATIONS WITH DATA FIDELITY TERM VIA AN ITERATIVELY REWEIGHTED LEAST SQUARES ALGORITHM [electronic resource]
Saved in:
| Online Access: |
Online Access |
|---|---|
| Corporate Author: | |
| Format: | Government Document Electronic eBook |
| Language: | English |
| Published: |
Los Alamos, N.M. : Oak Ridge, Tenn. :
Los Alamos National Laboratory ; distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy,
2007.
|
| Subjects: |
| Abstract: | Basis Pursuit and Basis Pursuit Denoising, well established techniques for computing sparse representations, minimize an ℓ² data fidelity term subject to an ℓ¹ sparsity constraint or regularization term on the solution by mapping the problem to a linear or quadratic program. Basis Pursuit Denoising with an ℓ¹ 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. |
|---|---|
| Item Description: | Published through the Information Bridge: DOE Scientific and Technical Information. 01/08/2007. "la-ur-07-0078" WOHLBERG, BRENDT; RODRIGUEZ, PAUL. |