High-dimensional analysis of semidefinite relaxations for sparse principal components

Principal component analysis (PCA) is a classical method for dimensionality reduction based on extracting the dominant eigenvectors of the sample covariance matrix. However, PCA is well known to behave poorly in the ``large , small '' setting, in which the problem dimension is comparable to or larger than the sample size . This paper studies PCA in this high-dimensional regime, but under the additional assumption that the maximal eigenvector is sparse, say, with at most nonzero components. We consider a spiked covariance model in which a base matrix is perturbed by adding a -sparse maximal eigenvector, and we analyze two computationally tractable methods for recovering the support set of this maximal eigenvector, as follows: (a) a simple diagonal thresholding method, which transitions from success to failure as a function of the rescaled sample size ; and (b) a more sophisticated semidefinite programming (SDP) relaxation, which succeeds once the rescaled sample size is larger than a critical threshold. In addition, we prove that no method, including the best method which has exponential-time complexity, can succeed in recovering the support if the order parameter is below a threshold. Our results thus highlight an interesting trade-off between computational and statistical efficiency in high-dimensional inference.
View on arXiv