A Mixed (2, p-like)-Norm Penalized Least Mean Squares Algorithm for Block-Sparse System Identification
A Mixed (2, p-like)-Norm Penalized Least Mean Squares Algorithm for Block-Sparse System Identification
复制标题
块稀疏系统辨识的混合(2, p-like)范数惩罚最小均方算法
DOI：
10.1007/s00034-018-0769-9
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Zheng Yahong Rosa
中科院分区：
文献类型：
--
作者：
Wei Ye;Zhang Yonggang;Wang Chengcheng;Zheng Yahong Rosa
本文提出了一种新的块稀疏系统辨识的混合（2，p-like）-范数惩罚最小均方（LMS）算法，其中未知系统的脉冲响应向量中的非零系数被构造成单个簇或多个簇。该算法将抽头权向量分成若干组大小相等的子向量，在原有均方误差代价函数的基础上，引入混合范数约束。范数约束下的参数取0 ~ 2之间的任意值，从而提高了块稀疏系统的辨识性能。研究了参数p和分组大小对算法性能的影响，并给出了选择这两个参数的一般准则，以便于实际应用。该方案的优点是不需要比较运算，而代数运算的阶数与块稀疏LMS算法相同。数值仿真结果表明，所提出的范数惩罚LMS算法优于现有的基于和范数的块稀疏性感知算法和单范数惩罚LMS策略。
This work presents a new mixed (2,p-like)-norm penalized least mean squares (LMS) algorithm for block-sparse system identifications where the nonzero coefficients in the impulse response vector of unknown systems are structured in a single cluster or multiple clusters. The new algorithm divides the tap-weight vector into groups of equal-sized sub-vectors and then introduces a mixed-norm constraint on the filter tap-weight vector in addition to the original mean-square-error cost function. The parameterpin the-norm constraint takes any value between zero and two, thus improving the identification performance of the block-sparse systems. The effect of the parameterpand the group size on the performance of the proposed algorithm is studied, and general guidelines for choosing these two parameters are provided to facilitate practical use. The advantage of the proposed scheme is that no comparison operations are required while algebraic operations are of the same order as the block-sparse LMS algorithm. Numerical simulations show that the proposed-norm penalized LMS algorithm outperforms the existing- and-norm-based block-sparsity-aware algorithms and single-norm penalized LMS strategies.