Streaming Kernel PCA with Õ(√(n)) Random Features

08/02/2018

∙

by   Enayat Ullah, et al.

∙

0

∙

share

We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, O(√(n) n) features suffices to achieve O(1/ϵ^2) sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Oja's algorithm that achieves this rate.