Within a number of compressed sensing (CS) problems, support recovery of sparse signals is the primary task that needs to be performed. In this paper, we propose a Q-learning based algorithm of support recovery (QSR) for sparse signals, which treats the atomic selection in traditional greedy CS algorithms as Markov Decision Process (MDP) in reinforcement learning (RL). We adopt parallel computing to address "the curse of dimensionality" in Q-learning, dividing the overall RL problem into multiple subproblems. The computational complexity can thus significantly decrease, which grows linearly with the increase of signal length. Experiments show that the proposed algorithm performs closely to other CS algorithms when dealing with high sparsity level signals and it has better performance when dealing with low sparsity level signals.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    QSR: Q-Learning Based Algorithm of Support Recovery for Sparse Signals


    Contributors:
    Zhou, Tianzhi (author) / Wang, Yibo (author) / Wu, Zhangyan (author) / Liang, Hengwei (author) / Qi, Yuan (author) / Qian, Rongrong (author)


    Publication date :

    2024-10-07


    Size :

    3008665 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    NN-based Support Detection of Sparse Signals

    Abolfathimomtaz, Abbas / Soleimanzade, Amirhosein / Ardakani, Masoud | IEEE | 2020


    Recovery probability analysis for sparse signals via OMP

    Mingbo Niu / Salari, Soheil / Chan, Francois et al. | IEEE | 2015


    A Robust Reconstruction Algorithm for Sparse Signals

    Hao, Wenjie / Qi, Chun | British Library Online Contents | 2015


    A Pseudo-Inverse-Based Hard Thresholding Algorithm for Sparse Signal Recovery

    Wen, Jinming / He, Hongyu / He, Zihao et al. | IEEE | 2023