Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel, Dimitrios Myrisiotis, A. Pavan, N. V. Vinodchandran
{"title":"产品分布的总变异距离是 $\\#\\mathsf{P}$ 完整的","authors":"Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel, Dimitrios Myrisiotis, A. Pavan, N. V. Vinodchandran","doi":"arxiv-2405.08255","DOIUrl":null,"url":null,"abstract":"We show that computing the total variation distance between two product\ndistributions is $\\#\\mathsf{P}$-complete. This is in stark contrast with other\ndistance measures such as Kullback-Leibler, Chi-square, and Hellinger, which\ntensorize over the marginals leading to efficient algorithms.","PeriodicalId":501024,"journal":{"name":"arXiv - CS - Computational Complexity","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Total Variation Distance for Product Distributions is $\\\\#\\\\mathsf{P}$-Complete\",\"authors\":\"Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel, Dimitrios Myrisiotis, A. Pavan, N. V. Vinodchandran\",\"doi\":\"arxiv-2405.08255\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We show that computing the total variation distance between two product\\ndistributions is $\\\\#\\\\mathsf{P}$-complete. This is in stark contrast with other\\ndistance measures such as Kullback-Leibler, Chi-square, and Hellinger, which\\ntensorize over the marginals leading to efficient algorithms.\",\"PeriodicalId\":501024,\"journal\":{\"name\":\"arXiv - CS - Computational Complexity\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computational Complexity\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2405.08255\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computational Complexity","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2405.08255","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Total Variation Distance for Product Distributions is $\#\mathsf{P}$-Complete
We show that computing the total variation distance between two product
distributions is $\#\mathsf{P}$-complete. This is in stark contrast with other
distance measures such as Kullback-Leibler, Chi-square, and Hellinger, which
tensorize over the marginals leading to efficient algorithms.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
