Sparse Proximal Support Vector Machines for feature selection in high dimensional datasets

作者：

Highlights：

• Sparse Proximal Support Vector Machines is an embedded feature selection method.

• sPSVMs removes more than 98% of features in many high dimensional datasets.

• An efficient alternating optimization technique is proposed.

• sPSVMs induces class-specific local sparsity.

摘要

•Sparse Proximal Support Vector Machines is an embedded feature selection method.•sPSVMs removes more than 98% of features in many high dimensional datasets.•An efficient alternating optimization technique is proposed.•sPSVMs induces class-specific local sparsity.

论文关键词：Embedded feature selection,Sparsity,Regularization,Class-specific feature selection,High dimensional datasets

论文评审过程：Received 26 May 2015, Revised 10 August 2015, Accepted 12 August 2015, Available online 20 August 2015, Version of Record 3 September 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.08.022