首页> 外文期刊>International Journal of Statistics and Probability >Improved Hoeffding’s Lemma and Hoeffding’s Tail Bounds
【24h】

Improved Hoeffding’s Lemma and Hoeffding’s Tail Bounds

机译:改善了Hoeffd的引理和Hoeffding的尾界

获取原文
           

摘要

The purpose of this article is to improve Hoeffding’s lemma and consequently Hoeffding’s tail bounds. The improvement pertains to left skewed zero mean random variables X ∈ [a, b], where a < 0 and ?a > b. The proof of Hoeffding’s improved lemma uses Taylor’s expansion, the convexity of exp(sx), s ∈ R, and an unnoticed observation since Hoeffding’s publication in 1963 that for ?a > b the maximum of the intermediate function τ(1 ? τ) appearing in Hoeffding’s proof is attained at an endpoint rather than at τ = 0.5 as in the case b > ?a. Using Hoeffding’s improved lemma we obtain one sided and two sided tail bounds for P(S n ≥ t) and P(|S n| ≥ t), respectively, where S n = Pn i=1 Xi and the Xi ∈ [ai , bi], i = 1, ..., n are independent zero mean random variables (not necessarily identically distributed). It is interesting to note that we could also improve Hoeffding’s two sided bound for all {Xi : ?ai , bi , i = 1, ..., n}. This is so because here the one sided bound should be increased by P(?S n ≥ t), wherein the left skewed intervals become right skewed and vice versa.
机译:本文的目的是改善Hoeffding的引理,因此霍夫丁的尾翼。改善偏离偏斜零平均随机变量x∈[a,b],其中<0和?a> b。 Hoeffding的改善的引理证明使用泰勒的扩张,Exp(SX),S∈r的凸性和自1963年的发布以来的不受注意的观察,因为它是出现的中间功能τ(1?τ)的最大值在Hoeffding的证据中,在端点而不是τ= 0.5处获得,如在案例中一样?a。使用Hoeffd的改善的引理我们可以分别获得一个侧面和双面尾部的p(sn≥t)和p(| s n |≥t),其中s n = pni i = 1 xi和xi∈[ai, Bi],i = 1,...,n是独立的零平均随机变量(不一定相同地分布)。值得注意的是,我们还可以改善Hoeffding的双面界限所有{xi:?ai,bi,i = 1,...,n}。这是因为这里应该通过p(Δsn≥t)增加一个面绑定,其中左偏斜间隔变为右倾斜,反之亦然。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号