Title :
Recent results on sparse principle component analysis
Author :
Cai, Tony T. ; Zongming Ma ; Yihong Wu
Author_Institution :
Dept. of Stat., Univ. of Pennsylvania, Philadelphia, PA, USA
Abstract :
Principal component analysis (PCA) is one of the most commonly used statistical procedures for dimension reduction. This paper presents some recent results on the minimax estimation of principal subspaces in high dimensions. Under mild technical conditions, we characterize the minimax risk for estimating the principal subspace under the quadratic loss within absolute constant factors.
Keywords :
data reduction; minimax techniques; principal component analysis; risk management; PCA; Sparse Principle Component Analysis; dimension reduction; minimax risk; multivariate analysis; principal subspace minimax estimation; quadratic loss; statistical procedures; Conferences; Convergence; Covariance matrices; Eigenvalues and eigenfunctions; Estimation; Principal component analysis; Sociology;
Conference_Titel :
Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2013 IEEE 5th International Workshop on
Conference_Location :
St. Martin
Print_ISBN :
978-1-4673-3144-9
DOI :
10.1109/CAMSAP.2013.6714037
