English

Improved analysis of randomized SVD for top-eigenvector approximation

Machine Learning 2022-02-17 v1 Numerical Analysis Numerical Analysis

Abstract

Computing the top eigenvectors of a matrix is a problem of fundamental interest to various fields. While the majority of the literature has focused on analyzing the reconstruction error of low-rank matrices associated with the retrieved eigenvectors, in many applications one is interested in finding one vector with high Rayleigh quotient. In this paper we study the problem of approximating the top-eigenvector. Given a symmetric matrix A\mathbf{A} with largest eigenvalue λ1\lambda_1, our goal is to find a vector \hu that approximates the leading eigenvector u1\mathbf{u}_1 with high accuracy, as measured by the ratio R(u^)=λ11u^TAu^/u^Tu^R(\hat{\mathbf{u}})=\lambda_1^{-1}{\hat{\mathbf{u}}^T\mathbf{A}\hat{\mathbf{u}}}/{\hat{\mathbf{u}}^T\hat{\mathbf{u}}}. We present a novel analysis of the randomized SVD algorithm of \citet{halko2011finding} and derive tight bounds in many cases of interest. Notably, this is the first work that provides non-trivial bounds of R(u^)R(\hat{\mathbf{u}}) for randomized SVD with any number of iterations. Our theoretical analysis is complemented with a thorough experimental study that confirms the efficiency and accuracy of the method.

Keywords

Cite

@article{arxiv.2202.07992,
  title  = {Improved analysis of randomized SVD for top-eigenvector approximation},
  author = {Ruo-Chun Tzeng and Po-An Wang and Florian Adriaens and Aristides Gionis and Chi-Jen Lu},
  journal= {arXiv preprint arXiv:2202.07992},
  year   = {2022}
}

Comments

Accepted to International Conference on Artificial Intelligence and Statistics (AISTATS) 2022

R2 v1 2026-06-24T09:40:41.114Z