Structural nonparallel support vector machine for pattern recognition

作者：

Highlights：

• We design a new structural nonparallel support vector machine (SNPSVM).

• SNPSVM can fully exploit prior knowledge in the datasets.

• We apply the alternating direction method of multipliers (ADMM) for SNPSVM.

• We apply the block and parallel techniques in our algorithms.

摘要

Highlights•We design a new structural nonparallel support vector machine (SNPSVM).•SNPSVM can fully exploit prior knowledge in the datasets.•We apply the alternating direction method of multipliers (ADMM) for SNPSVM.•We apply the block and parallel techniques in our algorithms.

论文关键词：Structural information,Nonparallel support vector machine,Alternating direction method of multipliers,Pattern recognition

论文评审过程：Received 23 September 2015, Revised 7 March 2016, Accepted 29 April 2016, Available online 17 May 2016, Version of Record 10 June 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.04.017