arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1402.3695math.STstat.TH
收藏

关于Bayes估计量的非渐近性

About the non-asymptotic behaviour of Bayes estimators

Lucien Birgé

摘要:

本文研究了由$n$ i.i.d.估计未知分布的Bayes方法的{ \em非渐近}性质。意见。我们假设先验是由一个模型$(\scr{S},h)$(其中$h$表示海林格距离)与适当的度量属性,涉及的小球,需要覆盖较大的。我们还要求先验在小球上放置足够的概率。我们考虑两种不同的情况。最简单的情况是一个参数模型包含的目标密度,我们表明,后集中在真实的分布率$1/\sqrt{n}$。在一般情况下,我们放松参数假设,并考虑到可能的错误指定的模型。假设真实分布和$\scr{S}$之间的Kullback-Leibler信息是有限的,我们建立了贝叶斯估计的风险界。

英文摘要:

This paper investigates the {\em nonasymptotic} properties of Bayes procedures for estimating an unknown distribution from $n$ i.i.d.\ observations. We assume that the prior is supported by a model $(\scr{S},h)$ (where $h$ denotes the Hellinger distance) with suitable metric properties involving the number of small balls that are needed to cover larger ones. We also require that the prior put enough probability on small balls. We consider two different situations. The simplest case is the one of a parametric model containing the target density for which we show that the posterior concentrates around the true distribution at rate $1/\sqrt{n}$. In the general situation, we relax the parametric assumption and take into account a possible mispecification of the model. Provided that the Kullback-Leibler Information between the true distribution and $\scr{S}$ is finite, we establish risk bounds for the Bayes estimators.

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。

↑