Tuning of the hyperparameters for L2-loss SVMs with the RBF kernel by the maximum-margin principle and the jackknife technique

作者：

Highlights：

• An efficient method is proposed to tune the hyperparameters for L2-loss RBF-SVMs.

• The kernel parameters are estimated by optimizing a margin-based criterion.

• The L2-soft-margin parameter C is determined by an analytic formula.

• Experimental results show that the proposed approach is efficient and accurate.

摘要

Highlights•An efficient method is proposed to tune the hyperparameters for L2-loss RBF-SVMs.•The kernel parameters are estimated by optimizing a margin-based criterion.•The L2-soft-margin parameter C is determined by an analytic formula.•Experimental results show that the proposed approach is efficient and accurate.

论文关键词：RBF kernels,L2-loss support vector machines,The jackknife method,Maximum-margin principles

论文评审过程：Received 29 July 2014, Revised 2 April 2015, Accepted 25 June 2015, Available online 6 July 2015, Version of Record 19 August 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.06.017