Ellipsoid Approximation Using Random Vectors
Abstract
We analyze the behavior of a random matrix with independent rows, each distributed according to the same probability measure on ${\mathbb R}^{n}$ or on ℓ_2. We investigate the spectrum of such a matrix and the way the ellipsoid generated by it approximates the covariance structure of the underlying measure. As an application, we provide estimates on the deviation of the spectrum of Gram matrices from the spectrum of the integral operator.
Cite
Text
Mendelson and Pajor. "Ellipsoid Approximation Using Random Vectors." Annual Conference on Computational Learning Theory, 2005. doi:10.1007/11503415_29Markdown
[Mendelson and Pajor. "Ellipsoid Approximation Using Random Vectors." Annual Conference on Computational Learning Theory, 2005.](https://mlanthology.org/colt/2005/mendelson2005colt-ellipsoid/) doi:10.1007/11503415_29BibTeX
@inproceedings{mendelson2005colt-ellipsoid,
title = {{Ellipsoid Approximation Using Random Vectors}},
author = {Mendelson, Shahar and Pajor, Alain},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2005},
pages = {429-443},
doi = {10.1007/11503415_29},
url = {https://mlanthology.org/colt/2005/mendelson2005colt-ellipsoid/}
}