ICLR 2020spotlight74 citations

Ridge Regression: Structure, Cross-Validation, and Sketching

Sifan Liu, Edgar Dobriban

Abstract

We study the following three fundamental problems about ridge regression: (1) what is the structure of the estimator? (2) how to correctly use cross-validation to choose the regularization parameter? and (3) how to accelerate computation without losing too much accuracy? We consider the three problems in a unified large-data linear model. We give a precise representation of ridge regression as a covariance matrix-dependent linear combination of the true parameter and the noise. We study the bias of $K$-fold cross-validation for choosing the regularization parameter, and propose a simple bias-correction. We analyze the accuracy of primal and dual sketching for ridge regression, showing they are surprisingly accurate. Our results are illustrated by simulations and by analyzing empirical data.

ridge regressionsketchingrandom matrix theorycross-validationhigh-dimensional asymptotics
BibTeX
@inproceedings{
Liu2020Ridge,
title={Ridge Regression: Structure, Cross-Validation, and Sketching},
author={Sifan Liu and Edgar Dobriban},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=HklRwaEKwB}
}