Stochastic IHT With Stochastic Polyak Step-Size for Sparse Signal Recovery

Sparse signal recovery arises from many applications. However, deterministic algorithms often require significant time, especially for large-scale systems. Hence, stochastic algorithms like the Stochastic Iterative Hard Thresholding Algorithm (StoIHT) were proposed to address large-scale problems. In this letter, we propose using the stochastic Polyak step size method to design step sizes and provide theoretical convergence analysis. Experimental results suggest that our algorithm demonstrates comparable performance to other stochastic algorithms in sparse signal recovery and image reconstruction with faster convergence.