Scaled-Gradient Hard Thresholding Algorithms for Sparse Signal Recovery
Abstract
Thresholding methods provide a simple iterative framework for sparse signal recovery by combining a search direction with a thresholding operation. Gradient-based search directions are computationally efficient because they require only first-order information for the error metric. We incorporate componentwise gradient scaling into this framework by preserving large-magnitude components and attenuating the remaining components of the gradient of error metric. Combining this strategy with hard thresholding yields scaled-gradient hard thresholding (SGHT) and its pursuit variant SGHTP. Under suitable restricted isometry conditions, we establish recovery error bounds for both methods that account for measurement noise and deviations from exact sparsity. Numerical experiments indicate that SGHTP achieves recovery performance comparable to established pursuit methods on the tested ECG signals.
Related
- Sparse descent subspace-Newton thresholding algorithm for sparse optimization problems
- High-Order Variable-Scaled Energetic Variational Neural Networks for Phase-Field Gradient Flows
- ParaDeAl: Parallel Descent Algorithms for Sparse Statistics
- Sparse Dictionary Learning for Measure-Valued Data via Linearized Optimal Transport: Efficient Algorithms and Sample Complexity
- Retraction-Based Gradient Projection Algorithms on Manifolds
BibTeX
@misc{meng2026scaledgradient,
title = {{Scaled-Gradient Hard Thresholding Algorithms for Sparse Signal Recovery}},
author = {Nan Meng and Yun-Bin Zhao},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.41302},
eprint = {2610.41302},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.41302},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Scaled-Gradient Hard Thresholding Algorithms for Sparse Signal Recovery
AU - Nan Meng
AU - Yun-Bin Zhao
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2610.41302
UR - https://arxiv.org/abs/2610.41302
AB - Thresholding methods provide a simple iterative framework for sparse signal recovery by combining a search direction with a thresholding operation. Gradient-based search directions are computationally efficient because they require only first-order information for the error metric. We incorporate componentwise gradient scaling into this framework by preserving large-magnitude components and attenuating the remaining components of the gradient of error metric. Combining this strategy with hard thresholding yields scaled-gradient hard thresholding (SGHT) and its pursuit variant SGHTP. Under suitable restricted isometry conditions, we establish recovery error bounds for both methods that account for measurement noise and deviations from exact sparsity. Numerical experiments indicate that SGHTP achieves recovery performance comparable to established pursuit methods on the tested ECG signals.
ER -