Tuning-free ridge estimators for high-dimensional generalized linear models
Methodology
2020-02-28 v1 Applications
Computation
Machine Learning
Abstract
Ridge estimators regularize the squared Euclidean lengths of parameters. Such estimators are mathematically and computationally attractive but involve tuning parameters that can be difficult to calibrate. In this paper, we show that ridge estimators can be modified such that tuning parameters can be avoided altogether. We also show that these modified versions can improve on the empirical prediction accuracies of standard ridge estimators combined with cross-validation, and we provide first theoretical guarantees.
Keywords
Cite
@article{arxiv.2002.11916,
title = {Tuning-free ridge estimators for high-dimensional generalized linear models},
author = {Shih-Ting Huang and Fang Xie and Johannes Lederer},
journal= {arXiv preprint arXiv:2002.11916},
year = {2020}
}