期刊
IEEE TRANSACTIONS ON INFORMATION THEORY
卷 67, 期 1, 页码 549-558出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIT.2020.3034539
关键词
Concentration inequality; relative entropy; likelihood ratio; multinomial; method of types; empirical distribution
资金
- ONR [N000141912446]
- U.S. Department of Defense (DOD) [N000141912446] Funding Source: U.S. Department of Defense (DOD)
The study investigates the relative entropy of the empirical probability vector with respect to the true probability vector in multinomial sampling, generalizing a recent result and showing the moment generating function of the statistic is bounded by a polynomial. By characterizing the family of polynomials and developing Chernoff-type tail bounds, including a closed-form version, the research demonstrates dominance over classic methods and competitiveness with the state of the art, as shown in an application to estimating the proportion of unseen butterflies.
We study the relative entropy of the empirical probability vector with respect to the true probability vector in multinomial sampling of k categories, which, when multiplied by sample size n, is also the log-likelihood ratio statistic. We generalize a recent result and show that the moment generating function of the statistic is bounded by a polynomial of degree n on the unit interval, uniformly over all true probability vectors. We characterize the family of polynomials indexed by (k, n) and obtain explicit formulae. Consequently, we develop Chernoff-type tail bounds, including a closed-form version from a large sample expansion of the bound minimizer. Our bound dominates the classic method-of-types bound and is competitive with the state of the art. We demonstrate with an application to estimating the proportion of unseen butterflies.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据