论文标题
对称属性估计的一般框架
A General Framework for Symmetric Property Estimation
论文作者
论文摘要
在本文中，我们提供了一个通用框架，用于估算I.I.D.分布的对称属性。样品。对于一类广泛的对称特性，我们确定了经验估计工作的简单区域以及需要更复杂估计器的困难区域。我们表明，通过大致计算该概况最大似然（PML）分布\ cite \ cite {ados16}在这个困难区域中，我们获得了一个对称属性估计框架，该框架是基于PML的先前通用估计方法中许多属性中许多属性的样本复杂性。基于这些伪PML分布的最终算法也更加实用。
In this paper we provide a general framework for estimating symmetric properties of distributions from i.i.d. samples. For a broad class of symmetric properties we identify the easy region where empirical estimation works and the difficult region where more complex estimators are required. We show that by approximately computing the profile maximum likelihood (PML) distribution \cite{ADOS16} in this difficult region we obtain a symmetric property estimation framework that is sample complexity optimal for many properties in a broader parameter regime than previous universal estimation approaches based on PML. The resulting algorithms based on these pseudo PML distributions are also more practical.
