Provable More Data Hurt in High Dimensional Least Squares Estimator
Machine Learning
2020-08-17 v1 Machine Learning
Applications
Abstract
This paper investigates the finite-sample prediction risk of the high-dimensional least squares estimator. We derive the central limit theorem for the prediction risk when both the sample size and the number of features tend to infinity. Furthermore, the finite-sample distribution and the confidence interval of the prediction risk are provided. Our theoretical results demonstrate the sample-wise nonmonotonicity of the prediction risk and confirm "more data hurt" phenomenon.
Cite
@article{arxiv.2008.06296,
title = {Provable More Data Hurt in High Dimensional Least Squares Estimator},
author = {Zeng Li and Chuanlong Xie and Qinwen Wang},
journal= {arXiv preprint arXiv:2008.06296},
year = {2020}
}