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

08/02/2018
by   Enayat Ullah, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/28/2013

Memory Limited, Streaming PCA

We consider streaming, one-pass principal component analysis (PCA), in t...
research
03/09/2023

Invertible Kernel PCA with Random Fourier Features

Kernel principal component analysis (kPCA) is a widely studied method to...
research
02/16/2018

Inferring relevant features: from QFT to PCA

In many-body physics, renormalization techniques are used to extract asp...
research
02/23/2016

An Improved Gap-Dependency Analysis of the Noisy Power Method

We consider the noisy power method algorithm, which has wide application...
research
02/21/2017

Stochastic Canonical Correlation Analysis

We tightly analyze the sample complexity of CCA, provide a learning algo...
research
12/16/2015

Streaming Kernel Principal Component Analysis

Kernel principal component analysis (KPCA) provides a concise set of bas...
research
10/11/2018

On Kernel Derivative Approximation with Random Fourier Features

Random Fourier features (RFF) represent one of the most popular and wide...

Please sign up or login with your details

Forgot password? Click here to reset