| 摘要: |
| 本文研究了一种给定的复杂网络结构识别问题.利用网络结构的稀疏性质,提出了一个带有l1正则化的最小二乘模型.数值仿真表明该算法对带噪声或不带噪声的较大型网络结构的识别是非常有效的. |
| 关键词: 复杂网络 结构识别 l1正则化 加权迭代最小二乘 牛顿方法 |
| DOI： |
| 分类号:O193;O224;O231.5;O241.81 |
| 基金项目:. |
|
| STRUCTURE IDENTIFICATION OF A SPARSE COMPLEX NETWORK |
|
KE Ting-ting
|
|
School of Mathematics and Statistics, Wuhan University, Wuhan 430072, China
|
| Abstract: |
| In this paper,we investigate the structure identification of a given complex network.By noticing the sparse structure of the network,we propose an l1-regularized output least squares model.Simulations show that the whole algorithm is very efficient for larger networks with or without noise. |
| Key words: complex network structure identification l1 regularization iteratively rewei ghted least squares Newton method |
