Raman Arora

Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features

2018 · arXiv (Cornell University)

We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, $O(\sqrt{n} \log n)$ features suffices to achieve $O(1/ε^2)$ sample complexity. Furthermore, we give …