SPARSE REPRESENTATIONS WITH DATA FIDELITY TERM VIA AN ITERATIVELY REWEIGHTED LEAST SQUARES ALGORITHM

Technical Report · Mon Jan 08 00:00:00 EST 2007

DOI:https://doi.org/10.2172/1000493· OSTI ID:1000493

WOHLBERG, BRENDT ^[1]; RODRIGUEZ, PAUL ^[1]

---

1. 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

Related Subjects

99 GENERAL AND MISCELLANEOUS
ALGORITHMS
LEAST SQUARE FIT
ITERATIVE METHODS