Theoretical Linear Convergence of Deep Unfolding Network for Block-Sparse Signal Recovery
arXiv:2111.09801
Abstract
In this paper, we consider the recovery of the high-dimensional block-sparse signal from a compressed set of measurements, where the non-zero coefficients of the recovered signal occur in a small number of blocks. Adopting the idea of deep unfolding, we explore the block-sparse structure and put forward a block-sparse reconstruction network named Ada-BlockLISTA, which performs gradient descent on every single block followed by a block-wise shrinkage. Furthermore, we prove the linear convergence rate of our proposed network, which also theoretically guarantees exact recovery for a potentially higher sparsity level based on underlyingblock structure. Numerical results indicate that Ada-BlockLISTA yields better signal recovery performance compared with existing algorithms, which ignore the additional block structure in the signal model.
arXiv comment12 pages, 7 figures, 35 conferences
References in corpus (8)
- Compressed Sensing of Block-Sparse Signals: Uncertainty Relations and Efficient Recovery
- Sparse Signal Recovery with Temporally Correlated Source Vectors Using Sparse Bayesian Learning
- AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
- Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds
- Multi-Carrier Agile Phased Array Radar
- Theoretical Analysis for Extended Target Recovery in Randomized Stepped Frequency Radars
- On some common compressive sensing recovery algorithms and applications - Review paper
- Proximal Gradient Algorithms: Applications in Signal Processing