变分距离的异常性

2006 IEEE Information Theory Workshop - ITW '06 Chengdu Pub Date : 2006-10-01 DOI:10.1109/ITW2.2006.323802

M. Khosravifard, D. Fooladivanda, T. Gulliver

{"title":"变分距离的异常性","authors":"M. Khosravifard, D. Fooladivanda, T. Gulliver","doi":"10.1109/ITW2.2006.323802","DOIUrl":null,"url":null,"abstract":"Csiszar f-divergences are an important class of distances for probability distributions. In particular, a well-known Csiszar f-divergence is the variational distance which is also a metric. Here, we prove that the variational distance is actually the unique Csiszar f-divergence which satisfies all metric conditions","PeriodicalId":299513,"journal":{"name":"2006 IEEE Information Theory Workshop - ITW '06 Chengdu","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2006-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Exceptionality of the Variational Distance\",\"authors\":\"M. Khosravifard, D. Fooladivanda, T. Gulliver\",\"doi\":\"10.1109/ITW2.2006.323802\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Csiszar f-divergences are an important class of distances for probability distributions. In particular, a well-known Csiszar f-divergence is the variational distance which is also a metric. Here, we prove that the variational distance is actually the unique Csiszar f-divergence which satisfies all metric conditions\",\"PeriodicalId\":299513,\"journal\":{\"name\":\"2006 IEEE Information Theory Workshop - ITW '06 Chengdu\",\"volume\":\"41 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2006-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2006 IEEE Information Theory Workshop - ITW '06 Chengdu\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ITW2.2006.323802\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2006 IEEE Information Theory Workshop - ITW '06 Chengdu","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITW2.2006.323802","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

Csiszar f-散度是概率分布的一类重要距离。特别地，一个著名的cisszar f散度是变分距离，它也是一个度规。在这里，我们证明了变分距离实际上是唯一的满足所有度量条件的cisszar f散度

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

Exceptionality of the Variational Distance

Csiszar f-divergences are an important class of distances for probability distributions. In particular, a well-known Csiszar f-divergence is the variational distance which is also a metric. Here, we prove that the variational distance is actually the unique Csiszar f-divergence which satisfies all metric conditions

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

2006 IEEE Information Theory Workshop - ITW '06 Chengdu

自引率

0.00%

发文量