Generalized discriminant analysis via kernel exponential families

作者：

Highlights：

• A novel supervised dimension reduction method using reproducing kernel Hilbert spaces.

• An infinite-dimensional version of exponential families enhances known solutions of sufficient dimension reduction.

• Support vector machines leads to an efficient estimation procedure for a sufficient dimension reduction.

摘要

•A novel supervised dimension reduction method using reproducing kernel Hilbert spaces.•An infinite-dimensional version of exponential families enhances known solutions of sufficient dimension reduction.•Support vector machines leads to an efficient estimation procedure for a sufficient dimension reduction.

论文关键词：Discriminant analysis,Sufficient dimension reduction,Reproducing kernel Hilbert spaces,Support vector machine

论文评审过程：Received 29 November 2021, Revised 1 May 2022, Accepted 21 July 2022, Available online 23 July 2022, Version of Record 5 August 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108933