Smoothly approximated support vector domain description

作者：

Highlights：

• Smoothly approximates the objective function of support vector domain description.

• Gradient based optimization method could be applied to the smoothed model.

• The proposed algorithms have asymptotic training complexity (n2).

• The algorithm is easy to implement, without requiring any optimization package.

摘要

Highlights•Smoothly approximates the objective function of support vector domain description.•Gradient based optimization method could be applied to the smoothed model.•The proposed algorithms have asymptotic training complexity (n2).•The algorithm is easy to implement, without requiring any optimization package.

论文关键词：Support vector domain description,Smooth approximation,Quadratic programming,conjugate gradient

论文评审过程：Received 14 February 2013, Revised 21 November 2014, Accepted 4 July 2015, Available online 17 July 2015, Version of Record 28 September 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.07.003