Stochastic Canonical Correlation Analysis

02/21/2017
by   Chao Gao, et al.
0

We tightly analyze the sample complexity of CCA, provide a learning algorithm that achieves optimal statistical performance in time linear in the required number of samples (up to log factors), as well as a streaming algorithm with similar guarantees.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2020

Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis

Variance reduction techniques have been successfully applied to temporal...
research
08/02/2018

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

We study the statistical and computational aspects of kernel principal c...
research
02/18/2023

Stochastic Approximation Approaches to Group Distributionally Robust Optimization

This paper investigates group distributionally robust optimization (GDRO...
research
11/18/2019

Estimating Entropy of Distributions in Constant Space

We consider the task of estimating the entropy of k-ary distributions fr...
research
02/06/2021

Streaming k-PCA: Efficient guarantees for Oja's algorithm, beyond rank-one updates

We analyze Oja's algorithm for streaming k-PCA and prove that it achieve...
research
12/20/2014

Competing with the Empirical Risk Minimizer in a Single Pass

In many estimation problems, e.g. linear and logistic regression, we wis...
research
02/23/2016

A Streaming Algorithm for Crowdsourced Data Classification

We propose a streaming algorithm for the binary classification of data b...

Please sign up or login with your details

Forgot password? Click here to reset