On information plus noise kernel random matrices
Author:
- Noureddine El KarouiNKNoureddine El Karoui
Open Access
- 1 October 2010
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 38 (5) , 3191-3216
Abstract
Kernel random matrices have attracted a lot of interest in recent years, from both practical and theoretical standpoints. Most of the theoretical work so far has focused on the case were the data is sampled from a low-dimensional structure. Very recently, the first results concerning kernel random matrices with high-dimensional input data were obtained, in a setting where the data was sampled from a genuinely high-dimensional structure—similar to standard assumptions in random matrix theory. In this paper, we consider the case where the data is of the type “information + noise.” In other words, each observation is the sum of two independent elements: one sampled from a “low-dimensional” structure, the signal part of the data, the other being high-dimensional noise, normalized to not overwhelm but still affect the signal. We consider two types of noise, spherical and elliptical. In the spherical setting, we show that the spectral properties of kernel random matrices can be understood from a new kernel matrix, computed only from the signal part of the data, but using (in general) a slightly different kernel. The Gaussian kernel has some special properties in this setting. The elliptical setting, which is important from a robustness standpoint, is less prone to easy interpretation.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- The spectrum of kernel random matricesThe Annals of Statistics, 2010
- Concentration of measure and spectra of random matrices: Applications to correlation matrices, elliptical distributions and beyondThe Annals of Applied Probability, 2009
- Towards a theoretical foundation for Laplacian-based manifold methodsJournal of Computer and System Sciences, 2008
- Operator norm consistent estimation of large-dimensional sparse covariance matricesThe Annals of Statistics, 2008
- Consistency of spectral clusteringThe Annals of Statistics, 2008
- High dimensional statistical inference and random matrices2007
- Statistical Properties of Kernel Principal Component Analysis2004
- On the distribution of the largest eigenvalue in principal components analysisThe Annals of Statistics, 2001
- Random Matrix Approximation of Spectra of Integral OperatorsBernoulli, 2000
- Concentration on the ℓ p n ball2000