arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.01892math.STcs.ITmath.ITstat.TH
收藏

稳健均值估计的信息下界

Information Lower Bounds for Robust Mean Estimation

Rémy Degenne, Timothée Mathieu

AI总结:

本文研究稳健均值估计的误差下界,利用 Fisher 信息及非参数极小化结果,统一给出参数、半参数与非参数情形下的紧下界及小错误概率最优估计量。

摘要:

我们证明了:在已知一个实值概率分布属于某个给定集合的条件下,任意用于估计该分布均值的估计量的误差下界。我们将这些下界同时应用于参数估计和非参数估计。在非参数情形中,我们将结果应用于有限方差分布的 sub-Gaussian(次高斯)估计问题,从而在小错误概率区间获得新的下界,并给出该区间内的最优估计量。在(半)参数情形中,我们利用 Fisher 信息给出依赖于分布的下界,这些下界在渐近意义下常数紧,量级为 $\sqrt{2\log(1/δ)/(nI)}$,其中 $I$ 是该分布的 Fisher 信息。我们利用某些非参数分布集合上已知的 Fisher 信息最小化子,在受污染分布、有界或半有界分布等情形中给出下界。

英文摘要:

We prove lower bounds on the error of any estimator for the mean of a real probability distribution under the knowledge that the distribution belongs to a given set. We apply these lower bounds both to parametric and nonparametric estimation. In the nonparametric case, we apply our results to the question of sub-Gaussian estimation for distributions with finite variance to obtain new lower bounds in the small error probability regime, and present an optimal estimator in that regime. In the (semi-)parametric case, we use the Fisher information to provide distribution-dependent lower bounds that are constant-tight asymptotically, of order $\sqrt{2\log(1/δ)/(nI)}$ where $I$ is the Fisher information of the distribution. We use known minimizers of the Fisher information on some nonparametric set of distributions to give lower bounds in cases such as corrupted distributions, or bounded/semi-bounded distributions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑