有限字母的相对熵和rsamnyi散度作为总变异距离函数的上界

2015 IEEE Information Theory Workshop - Fall (ITW) Pub Date : 2015-03-11 DOI:10.1109/ITWF.2015.7360766

I. Sason, S. Verdú

{"title":"有限字母的相对熵和rsamnyi散度作为总变异距离函数的上界","authors":"I. Sason, S. Verdú","doi":"10.1109/ITWF.2015.7360766","DOIUrl":null,"url":null,"abstract":"A new upper bound on the relative entropy is derived as a function of the total variation distance for probability measures defined on a common finite alphabet. The bound improves a previously reported bound by Csiszár and Talata. It is further extended to an upper bound on the Rényi divergence of an arbitrary non-negative order (including ∞) as a function of the total variation distance.","PeriodicalId":281890,"journal":{"name":"2015 IEEE Information Theory Workshop - Fall (ITW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"29","resultStr":"{\"title\":\"Upper bounds on the relative entropy and Rényi divergence as a function of total variation distance for finite alphabets\",\"authors\":\"I. Sason, S. Verdú\",\"doi\":\"10.1109/ITWF.2015.7360766\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A new upper bound on the relative entropy is derived as a function of the total variation distance for probability measures defined on a common finite alphabet. The bound improves a previously reported bound by Csiszár and Talata. It is further extended to an upper bound on the Rényi divergence of an arbitrary non-negative order (including ∞) as a function of the total variation distance.\",\"PeriodicalId\":281890,\"journal\":{\"name\":\"2015 IEEE Information Theory Workshop - Fall (ITW)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-03-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"29\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 IEEE Information Theory Workshop - Fall (ITW)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ITWF.2015.7360766\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE Information Theory Workshop - Fall (ITW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITWF.2015.7360766","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 29

摘要

本文导出了相对熵的一个新的上界，它是定义在一般有限字母上的概率测度的总变异距离的函数。该绑定改进了先前由Csiszár和Talata报道的绑定。进一步将其推广到任意非负阶(包括∞)的r nyi散度作为总变异距离的函数的上界。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Upper bounds on the relative entropy and Rényi divergence as a function of total variation distance for finite alphabets

A new upper bound on the relative entropy is derived as a function of the total variation distance for probability measures defined on a common finite alphabet. The bound improves a previously reported bound by Csiszár and Talata. It is further extended to an upper bound on the Rényi divergence of an arbitrary non-negative order (including ∞) as a function of the total variation distance.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2015 IEEE Information Theory Workshop - Fall (ITW)

自引率

0.00%

发文量