English

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.

Keywords

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}
}
R2 v1 2026-06-23T17:51:27.757Z