Minimax bounds for sparse PCA with noisy high-dimensional data
Open Access
- 1 June 2013
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 41 (3) , 1055-1084
Abstract
We study the problem of estimating the leading eigenvectors of a high-dimensional population covariance matrix based on independent Gaussian observations. We establish a lower bound on the minimax risk of estimators under the $l_{2}$ loss, in the joint limit as dimension and sample size increase to infinity, under various models of sparsity for the population eigenvectors. The lower bound on the risk points to the existence of different regimes of sparsity of the eigenvectors. We also propose a new method for estimating the eigenvectors by a two-stage coordinate selection scheme.
Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- High-dimensional analysis of semidefinite relaxations for sparse principal componentsThe Annals of Statistics, 2009
- On Consistency and Sparsity for Principal Components Analysis in High DimensionsJournal of the American Statistical Association, 2009
- DiscussionJournal of the American Statistical Association, 2009
- A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysisBiostatistics, 2009
- Generalized Thresholding of Large Covariance MatricesJournal of the American Statistical Association, 2009
- Finite sample approximation results for principal component analysis: A matrix perturbation approachThe Annals of Statistics, 2008
- Covariance regularization by thresholdingThe Annals of Statistics, 2008
- Sparse Principal Component AnalysisJournal of Computational and Graphical Statistics, 2006
- Chi-square oracle inequalities2001
- Information-theoretic determination of minimax rates of convergenceThe Annals of Statistics, 1999