An Improved Hard Thresholding Pursuit Algorithm for Compressive Sensing

Abstract

The tail- ℓ1 minimization model greatly improves the sparse signal recovery ability compared with ℓ1 minimization model. However, solving the tail- ℓ1 minimization problem requires high computational cost and a lot of time. The hard thresholding pursuit (HTP) technology is attractive due to its computational efficiency in practice. Inspired by the HTP technology, the HTP technology is considered to be an efficient technique to solve the tail- ℓ1 minimization problem. This paper introduces an improved HTP technology, namely tail-HTP. The tail-HTP technology retains the computational simplicity of the HTP technology and greatly improves the efficiency of solving the tail- ℓ1 minimization problem. In addition, the tail-HTP technology also improves the sparse signal recovery ability of the HTP technology. The experimental results verify the high efficiency and superior sparse signal recovery ability of the tail-HTP technology.