Robust penalized dantzig selector: Error analysis, oracle inequalities, and algorithmic efficiency
Open Access
- 1 January 2027
- journal article
- Published by American Institute of Mathematical Sciences (AIMS) in Inverse Problems and Imaging
- Vol. 26, 1-31
Abstract
This article addresses the recovery of sparse signals and low-rank matrices from limited, noisy observations. We introduce unconstrained models, termed the Robust Penalized Dantzig Vector Selector (RPDvS) for sparse signal recovery and the Robust Penalized Dantzig Matrix Selector (RPDmS) for low-rank matrix recovery. Under restricted isometry assumptions on the measurement operators, we establish stable recovery error bounds and oracle inequalities for both models in the presence of Gaussian noise. For the RPDmS model, we derive a tight oracle inequality that guarantees identification of a "nearly perfect'' column space and motivates a simple post-processing procedure that yields an improved estimator, thereby bridging a gap in the earlier analysis of the Dantzig matrix selector by Candès and Plan (2011). Parallel oracle-type results are obtained for the RPDvS model. Building on these theoretical guarantees, we develop efficient algorithms for solving the RPDvS and RPDmS problems and implement the proposed post-processing steps. Extensive simulations and empirical studies demonstrate that the new methods are computationally competitive while achieving superior reconstruction accuracy in both sparse signal and low-rank matrix recovery, thereby confirming the sharpness of our error bounds and the effectiveness of the algorithms.Keywords
This publication has 44 references indexed in Scilit:
- Sparse Recovery: The Square of $\ell _1/\ell _2$ NormsJournal of Scientific Computing, 2024
- A proximal algorithm with backtracked extrapolation for a class of structured fractional programmingApplied and Computational Harmonic Analysis, 2022
- Low-rank matrix recovery via regularized nuclear norm minimizationApplied and Computational Harmonic Analysis, 2021
- A partially proximal linearized alternating minimization method for finding Dantzig selectorsComputational and Applied Mathematics, 2021
- Signal recovery under mutual incoherence property and oracle inequalitiesFrontiers of Mathematics in China, 2018
- Sparse recovery with coherent tight frames via analysis Dantzig selector and analysis LASSOApplied and Computational Harmonic Analysis, 2014
- A non-convex algorithm framework based on DC programming and DCA for matrix completionNumerical Algorithms, 2014
- Multi-step fixed-point proximity algorithms for solving a class of optimization problems arising from image processingAdvances in Computational Mathematics, 2014
- Sharp RIP bound for sparse signal and low-rank matrix recoveryApplied and Computational Harmonic Analysis, 2013
- A First-Order Primal-Dual Algorithm for Convex Problems with Applications to ImagingJournal of Mathematical Imaging and Vision, 2010