Dimension-free PAC-Bayesian bounds for matrices, vectors, and linear least squares regression
Statistics Theory
2018-01-03 v2 Statistics Theory
Abstract
This paper is focused on dimension-free PAC-Bayesian bounds, under weak polynomial moment assumptions, allowing for heavy tailed sample distributions. It covers the estimation of the mean of a vector or a matrix, with applications to least squares linear regression. Special efforts are devoted to the estimation of Gram matrices, due to their prominent role in high-dimension data analysis.
Cite
@article{arxiv.1712.02747,
title = {Dimension-free PAC-Bayesian bounds for matrices, vectors, and linear least squares regression},
author = {Olivier Catoni and Ilaria Giulini},
journal= {arXiv preprint arXiv:1712.02747},
year = {2018}
}
Comments
Version 1 needed some further proofreading