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 1502.00326cs.ITmath.IT
收藏

Shannon熵的自适应估计

Adaptive Estimation of Shannon Entropy

Yanjun Han, Jiantao Jiao, Tsachy Weissman

摘要:

我们考虑从$n$ i.i.d.估计离散分布$P$的香农熵。样品最近,Jiao,Venkat,Han,Weissman,Wu和Yang构造了近似理论估计,在估计熵时达到了极小极大$L_2$率.它们的估计量在给定$n \gg \frac{S}{\ln S}$样本下是一致的,其中$S$是字母表大小,并且它是最佳可能的样本复杂度。相比之下,最大似然估计(MLE),即经验熵,需要$n\gg S$样本。在本论文中,我们显着细化现有工作的极大极小结果。为了减轻最小最大性的悲观主义,我们采用自适应估计框架,并表明,在焦,文卡特,韩,和韦斯曼的最小最大率最优估计达到最小最大率同时在一个嵌套序列的子集分布$P$,不知道字母表大小$S$或哪个子集$P$在于。换句话说,它们的估计量相对于参数空间的嵌套序列是自适应的,其特征在于分布的熵。我们还描述了最大似然估计在这个嵌套序列的最大风险,并显示,对于序列中的每个子集,与$n$样本的极小极大率最优估计的性能基本上是与$n\ln n$样本的极大似然估计,从而进一步证实了焦,文卡特,韩和韦斯曼所确定的现象的一般性。

英文摘要:

We consider estimating the Shannon entropy of a discrete distribution $P$ from $n$ i.i.d. samples. Recently, Jiao, Venkat, Han, and Weissman, and Wu and Yang constructed approximation theoretic estimators that achieve the minimax $L_2$ rates in estimating entropy. Their estimators are consistent given $n \gg \frac{S}{\ln S}$ samples, where $S$ is the alphabet size, and it is the best possible sample complexity. In contrast, the Maximum Likelihood Estimator (MLE), which is the empirical entropy, requires $n\gg S$ samples. In the present paper we significantly refine the minimax results of existing work. To alleviate the pessimism of minimaxity, we adopt the adaptive estimation framework, and show that the minimax rate-optimal estimator in Jiao, Venkat, Han, and Weissman achieves the minimax rates simultaneously over a nested sequence of subsets of distributions $P$, without knowing the alphabet size $S$ or which subset $P$ lies in. In other words, their estimator is adaptive with respect to this nested sequence of the parameter space, which is characterized by the entropy of the distribution. We also characterize the maximum risk of the MLE over this nested sequence, and show, for every subset in the sequence, that the performance of the minimax rate-optimal estimator with $n$ samples is essentially that of the MLE with $n\ln n$ samples, thereby further substantiating the generality of the phenomenon identified by Jiao, Venkat, Han, and Weissman.

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。

↑