|国家预印本平台
首页|Revisiting mean estimation over $\ell_p$ balls: Is the MLE optimal?

Revisiting mean estimation over $\ell_p$ balls: Is the MLE optimal?

Revisiting mean estimation over $\ell_p$ balls: Is the MLE optimal?

来源:Arxiv_logoArxiv
英文摘要

We revisit the problem of mean estimation on $\ell_p$ balls under additive Gaussian noise. When $p$ is strictly less than $2$, it is well understood that rate-optimal estimators must be nonlinear in the observations. In this work, we study the maximum likelihood estimator (MLE), which may be viewed as a nonlinear shrinkage procedure for mean estimation over $\ell_p$ balls. We demonstrate two phenomena for the behavior of the MLE, which depend on the noise level, the radius of the norm constraint, the dimension, and the norm index $p$. First, as a function of the dimension, for $p$ near $1$ or at least $2$, the MLE is minimax rate-optimal for all noise levels and all constraint radii. On the other hand, for $p$ between $1$ and $2$, there is a more striking behavior: for essentially all noise levels and radii for which nonlinear estimates are required, the MLE is minimax rate-suboptimal, despite being nonlinear in the observations. Our results also imply similar conclusions when given $n$ independent and identically distributed Gaussian samples, where we demonstrate that the MLE can be suboptimal by a polynomial factor in the sample size. Our lower bounds are constructive: whenever the MLE is rate-suboptimal, we provide explicit instances on which the MLE provably incurs suboptimal risk.

Liviu Aolaritei、Michael I. Jordan、Reese Pathak、Annie Ulichney

数学

Liviu Aolaritei,Michael I. Jordan,Reese Pathak,Annie Ulichney.Revisiting mean estimation over $\ell_p$ balls: Is the MLE optimal?[EB/OL].(2025-06-12)[2025-06-20].https://arxiv.org/abs/2506.10354.点此复制

评论