Streaming Kernel PCA with O(n) Random Features
2018-08-02Code Available0· sign in to hype
Enayat Ullah, Poorya Mianjy, Teodor V. Marinov, Raman Arora
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/r3831/SAKPCAOfficialnone★ 0
Abstract
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/^2) sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Oja's algorithm that achieves this rate.