Ambedkar Dukkipati, Narasimha Murty Musti, S. Bhatnagar
{"title":"Properties of Kullback-Leibler cross-entropy minimization in nonextensive framework","authors":"Ambedkar Dukkipati, Narasimha Murty Musti, S. Bhatnagar","doi":"10.1109/ISIT.2005.1523773","DOIUrl":null,"url":null,"abstract":"Kullback-Leibler cross-entropy has unique properties in cases involving distributions resulting from cross-entropy minimization. Nonextensive entropy (Tsallis entropy), which is a one-parameter generalization of Shannon entropy, is proposed to study certain class of physical systems. Thermostatistics based on Tsallis entropy is termed as nonextensive statistics or Tsallis statistics. Previously, Kullback-Leibler cross-entropy has been generalized and studied in this framework. In this paper we study properties of generalized cross-entropy minimization and present some differences with the classical case. In the representation of such a minimum cross-entropy distribution, we highlight the use of the q-product, an operator that has been recently introduced, to derive the mathematical structure behind the Tsallis statistics. One of our main results is the generalization of the triangle equality of cross-entropy minimization, in nonextensive framework","PeriodicalId":166130,"journal":{"name":"Proceedings. International Symposium on Information Theory, 2005. ISIT 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2005-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. International Symposium on Information Theory, 2005. ISIT 2005.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISIT.2005.1523773","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9
Abstract
Kullback-Leibler cross-entropy has unique properties in cases involving distributions resulting from cross-entropy minimization. Nonextensive entropy (Tsallis entropy), which is a one-parameter generalization of Shannon entropy, is proposed to study certain class of physical systems. Thermostatistics based on Tsallis entropy is termed as nonextensive statistics or Tsallis statistics. Previously, Kullback-Leibler cross-entropy has been generalized and studied in this framework. In this paper we study properties of generalized cross-entropy minimization and present some differences with the classical case. In the representation of such a minimum cross-entropy distribution, we highlight the use of the q-product, an operator that has been recently introduced, to derive the mathematical structure behind the Tsallis statistics. One of our main results is the generalization of the triangle equality of cross-entropy minimization, in nonextensive framework