Nyström-based approximate kernel subspace learning

作者：

Highlights：

• We propose a method for determining a subspace of the kernel space.

• We follow an approximate kernel learning approach for fast calculations.

• We test our approach in nonlinear large-scale classification problems.

摘要

Highlights•We propose a method for determining a subspace of the kernel space.•We follow an approximate kernel learning approach for fast calculations.•We test our approach in nonlinear large-scale classification problems.

论文关键词：Nonlinear pattern recognition,Kernel methods,Nonlinear projection trick,Nyström approximation

论文评审过程：Received 6 November 2015, Revised 26 February 2016, Accepted 12 March 2016, Available online 19 March 2016, Version of Record 6 May 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.03.018