提出L1范数正则化支持向量机(SVM)聚类算法.该算法能够同时实现聚类和特征选择功能.给出LI范数正则化SVM聚类原问题和对偶问题形式,采用类似迭代坐标下降的方法求解困难的混合整数规划问题.在多组数据集上的实验结果表明,L1范数正则化SVM聚类算法聚类准确率与L2范数正则化SVM聚类算法相近,而且能够实现特征选择.%This paper proposes a Ll-norm regularized Support Vector Machine(SVM) clustering algorithm. The proposed clustering algorithm can fulfill simultaneous clustering construction and feature selection. Primal and dual form of Ll-norm regularized SVM clustering problem is introduced, and an algorithm that iterates coodinate-wise desent approach is adopted to solve difficult mixed integer programming. Experimental results on real datasets show that the predict accuracy of the presented algorithm is compared with L2-norm regularized SVM clustering algorithm, and can take feature selection.
展开▼