An elementary analysis of ridge regression with random design
Statistics Theory
2022-10-11 v2 Machine Learning
Machine Learning
Statistics Theory
Abstract
In this note, we provide an elementary analysis of the prediction error of ridge regression with random design. The proof is short and self-contained. In particular, it bypasses the use of Rudelson's deviation inequality for covariance matrices, through a combination of exchangeability arguments, matrix perturbation and operator convexity.
Cite
@article{arxiv.2203.08564,
title = {An elementary analysis of ridge regression with random design},
author = {Jaouad Mourtada and Lorenzo Rosasco},
journal= {arXiv preprint arXiv:2203.08564},
year = {2022}
}
Comments
fixes a typo, small changes; 9 pages