file.pdf (377.49 kB)

Minimax Sparse Principal Subspace Estimation in High Dimensions

Download (377.49 kB)
journal contribution
posted on 01.12.2005, 00:00 by Vincent Q. Vu, Jing Lei

We study sparse principal components analysis in high dimensions, where p (the number of variables) can be much larger than n (the number of observations), and analyze the problem of estimating the subspace spanned by the principal eigenvectors of the population covariance matrix. We prove optimal, non-asymptotic lower and upper bounds on the minimax subspace estimation error under two different, but related notions of ℓq subspace sparsity for 0 ≤ q ≤ 1. Our upper bounds apply to general classes of covariance matrices, and they show that ℓq constrained estimates can achieve optimal minimax rates without restrictive spiked covariance conditions.


Publisher Statement

All Rights Reserved