ℓp-Norm Support Vector Data Description

作者：

Highlights：

• The support vector data description method optimises an-norm cost w.r.t. errors

• We generalise this modelling formalism to an-norm () slack penalty function

• The proposed method enables formulating a non-linear cost function w.r.t. errors

• Through a dual-norm, it introduces a controlling mechanism over the relative sparsity

• Experiments confirm the merits of the proposed method against other alternatives

摘要

•The support vector data description method optimises an-norm cost w.r.t. errors•We generalise this modelling formalism to an-norm () slack penalty function•The proposed method enables formulating a non-linear cost function w.r.t. errors•Through a dual-norm, it introduces a controlling mechanism over the relative sparsity•Experiments confirm the merits of the proposed method against other alternatives

论文关键词：One-class classification,Kernel methods,Support vector data description,ℓp-norm penalty

论文评审过程：Received 15 March 2022, Revised 22 June 2022, Accepted 21 July 2022, Available online 23 July 2022, Version of Record 27 July 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108930