Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors

arXiv:2305.12883v3 Announce Type: replace-cross
Abstract: In recent years, there has been a significant growth in research focusing on minimum $\ell_2$ norm (ridgeless) interpolation least squares estimators. However, the majority of these analyses have been limited to an unrealistic regression error structure, assuming independent and identically distributed errors with zero mean and common variance. In this paper, we explore prediction risk as well as estimation risk under more general regression error assumptions, highlighting the benefits of overparameterization in a more realistic …

abstract arxiv assumptions cs.lg econ.em error errors estimator general growth however independent interpolation least math.st minimum norm prediction regression replace research risk squares stat.ml stat.th type