On information plus noise kernel random matrices
El Karoui, Noureddine
Ann. Statist., Tome 38 (2010) no. 1, p. 3191-3216 / Harvested from Project Euclid
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.
Publié le : 2010-10-15
Classification:  Kernel matrices,  multivariate statistical analysis,  high-dimensional inference,  random matrix theory,  machine learning,  concentration of measure,  62H10,  60F99
@article{1284391762,
     author = {El Karoui, Noureddine},
     title = {On information plus noise kernel random matrices},
     journal = {Ann. Statist.},
     volume = {38},
     number = {1},
     year = {2010},
     pages = { 3191-3216},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1284391762}
}
El Karoui, Noureddine. On information plus noise kernel random matrices. Ann. Statist., Tome 38 (2010) no. 1, pp.  3191-3216. http://gdmltest.u-ga.fr/item/1284391762/