arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.04650math.STcs.LGstat.TH
收藏

概率单纯形上粗差抗差估计的置信区域和Minimax率

Confidence regions and minimax rates in outlier-robust estimation on the probability simplex

Amir-Hossein Bateni, Arnak S. Dalalyan

摘要:

我们考虑的问题估计的平均值的分布支持的$k$维概率单纯形的设置中的一个$\varepsilon$分数的观察受到对抗腐败。一个简单的具体例子是估计离散随机变量的分布的问题。假设离散变量取$k$值,则未知参数$\boldsymbol θ$是属于概率单形的$k$维向量。我们首先描述了各种设置的污染,并讨论这些设置之间的关系。然后,我们建立极小极大率时,估计的质量是由总变差距离,海林格距离,或$\mathbb L^2$ -距离之间的两个概率测度。我们还提供了置信区域的未知的意思,缩小在最小最大率。我们的分析表明,与这三个距离相关的极大极小率都是不同的,但它们都是通过样本平均值获得的。此外,我们表明,后者是自适应的未知向量的可能的稀疏性。一些数值实验说明我们的理论研究结果的报告。

英文摘要:

We consider the problem of estimating the mean of a distribution supported by the $k$-dimensional probability simplex in the setting where an $\varepsilon$ fraction of observations are subject to adversarial corruption. A simple particular example is the problem of estimating the distribution of a discrete random variable. Assuming that the discrete variable takes $k$ values, the unknown parameter $\boldsymbol θ$ is a $k$-dimensional vector belonging to the probability simplex. We first describe various settings of contamination and discuss the relation between these settings. We then establish minimax rates when the quality of estimation is measured by the total-variation distance, the Hellinger distance, or the $\mathbb L^2$-distance between two probability measures. We also provide confidence regions for the unknown mean that shrink at the minimax rate. Our analysis reveals that the minimax rates associated to these three distances are all different, but they are all attained by the sample average. Furthermore, we show that the latter is adaptive to the possible sparsity of the unknown vector. Some numerical experiments illustrating our theoretical findings are reported.

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。

↑