Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation

11/20/2018
by   Kush Bhatia, et al.
0

In this paper, we study the problems of principal Generalized Eigenvector computation and Canonical Correlation Analysis in the stochastic setting. We propose a simple and efficient algorithm, Gen-Oja, for these problems. We prove the global convergence of our algorithm, borrowing ideas from the theory of fast-mixing Markov chains and two-time-scale stochastic approximation, showing that it achieves the optimal rate of convergence. In the process, we develop tools for understanding stochastic processes with Markovian noise which might be of independent interest.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/04/2021

Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise

We study the so-called two-time-scale stochastic approximation, a simula...
research
07/24/2019

P-SLOCAL-Completeness of Maximum Independent Set Approximation

We prove that the maximum independent set approximation problem with pol...
research
12/29/2021

Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems

Motivated by the problem of online canonical correlation analysis, we pr...
research
05/26/2011

Efficient Learning of Sparse Invariant Representations

We propose a simple and efficient algorithm for learning sparse invarian...
research
09/06/2013

Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application

We provide an elementary proof of a simple, efficient algorithm for comp...
research
11/10/2020

LinCbO: fast algorithm for computation of the Duquenne-Guigues basis

We propose and evaluate a novel algorithm for computation of the Duquenn...
research
06/12/2019

Tensor Canonical Correlation Analysis

In many applications, such as classification of images or videos, it is ...

Please sign up or login with your details

Forgot password? Click here to reset