基于DC规划方法的稀疏临近支持向量机  

Sparse proximal support vector machines via DC programming

作　　者：杨琳希 李国权 YANG Linxi;LI Guoquan(School of Mathematical Sciences,Chongqing Normal University,Chongqing 401331,China)

机构地区：[1]重庆师范大学数学科学学院,重庆401331

出　　处：《运筹学学报》2020年第3期115-126,共12页Operations Research Transactions

基　　金：国家自然科学基金(No.11871128);重庆市自然科学基金(Nos.cstc2019jcyj-msxmX0282,cstc2019jcyj-msxmX0368);重庆市教委科技项目(No.KJQN201900531)。

摘　　要：为了提高临近支持向量机(PSVM)的数值表现,在PSVM的模型中引入了l0-范数正则项,提出了稀疏临近支持向量机模型(SPSVM),从而提高分类器的特征选择能力。然而带有l0-范数正则项的问题往往是NP-难问题,为了克服这一问题,采用非凸连续函数近似l0-范数,并通过适当的DC分解将问题转化成DC规划问题进行求解,同时还讨论了算法的收敛性。数值实验结果表明不论是在仿真数据还是在实际数据中,所提出的方法是比较有效稳定的。To improve the performance of proximal support vector machine,a new sparse proximal support vector machine is proposed in this paper where l0-norm regularization is used to improve the feature selection ability of the new model.However,problem with l0-norm regularization usually is NP-hard.To overcome this difficulty,a continuous nonconvex function is used to approximate l0-norm.With proper DC decomposition,we transform the problem into a DC programming problem which can be solved efficiently by DC algorithm.Meanwhile,we also discuss the convergence properties of our algorithm.The experimental results on both simulated and real datasets demonstrate the efficiency of the proposed algorithms.

关 键 词：临近支持向量机 稀疏优化 DC规划 特征选择 

分 类 号：O224[理学—运筹学与控制论] TP181[理学—数学]