Open Access
2010 Second order accurate distributed eigenvector computation for extremely large matrices
Noureddine El Karoui, Alexandre d’Aspremont
Electron. J. Statist. 4: 1345-1385 (2010). DOI: 10.1214/10-EJS577


We propose a second-order accurate method to estimate the eigenvectors of extremely large matrices thereby addressing a problem of relevance to statisticians working in the analysis of very large datasets. More specifically, we show that averaging eigenvectors of randomly subsampled matrices efficiently approximates the true eigenvectors of the original matrix under certain conditions on the incoherence of the spectral decomposition. This incoherence assumption is typically milder than those made in matrix completion and allows eigenvectors to be sparse. We discuss applications to spectral methods in dimensionality reduction and information retrieval.


Download Citation

Noureddine El Karoui. Alexandre d’Aspremont. "Second order accurate distributed eigenvector computation for extremely large matrices." Electron. J. Statist. 4 1345 - 1385, 2010.


Published: 2010
First available in Project Euclid: 30 November 2010

zbMATH: 1329.65074
MathSciNet: MR2738536
Digital Object Identifier: 10.1214/10-EJS577

Rights: Copyright © 2010 The Institute of Mathematical Statistics and the Bernoulli Society

Back to Top