Work

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

Year: 2018

Type: preprint

Abstract: 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 a memory efficient streaming algorithm based on classical Oja's algorithm that achieves this rate.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1808.00934

Authors: Ullah, Enayat, Mianjy, Poorya, Marinov, Teodor V., Arora, Raman

Institution: Johns Hopkins University

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2885310221

Cites:

Cited by: 1

Related to: 20