{"title":"消息传递估计算法的收敛性","authors":"J. Dauwels","doi":"10.1109/ISIT.2007.4557604","DOIUrl":null,"url":null,"abstract":"The convergence and stability properties of several message-passing estimation algorithms are investigated, i.e., (generalized) expectation maximization, gradient methods, and coordinate ascent/descent. Results are presented for cycle-free and cyclic factor graphs.","PeriodicalId":193467,"journal":{"name":"2007 IEEE International Symposium on Information Theory","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"On Convergence Properties of Message-Passing Estimation Algorithms\",\"authors\":\"J. Dauwels\",\"doi\":\"10.1109/ISIT.2007.4557604\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The convergence and stability properties of several message-passing estimation algorithms are investigated, i.e., (generalized) expectation maximization, gradient methods, and coordinate ascent/descent. Results are presented for cycle-free and cyclic factor graphs.\",\"PeriodicalId\":193467,\"journal\":{\"name\":\"2007 IEEE International Symposium on Information Theory\",\"volume\":\"4 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-06-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 IEEE International Symposium on Information Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISIT.2007.4557604\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 IEEE International Symposium on Information Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISIT.2007.4557604","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
On Convergence Properties of Message-Passing Estimation Algorithms
The convergence and stability properties of several message-passing estimation algorithms are investigated, i.e., (generalized) expectation maximization, gradient methods, and coordinate ascent/descent. Results are presented for cycle-free and cyclic factor graphs.