{"title":"加权中餐厅流程","authors":"A. Lo","doi":"10.1142/S0219607705000073","DOIUrl":null,"url":null,"abstract":"A class of distributions on partitions of a finite collection of objects is defined. The probability of a specific partition is a product of functions of clusters of the partition with the product running over all clusters. This class contains Chinese restaurant processes as a special case. The simulation of a distribution in this class is described through the seating probability that gives the conditional probability of joining a new object to an existing cluster. Examples in Bayesian mixture models are given.","PeriodicalId":80753,"journal":{"name":"Bulletin - Cosmos Club. Cosmos Club (Washington, D.C.)","volume":"65 1","pages":"107-111"},"PeriodicalIF":0.0000,"publicationDate":"2005-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":"{\"title\":\"WEIGHTED CHINESE RESTAURANT PROCESSES\",\"authors\":\"A. Lo\",\"doi\":\"10.1142/S0219607705000073\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A class of distributions on partitions of a finite collection of objects is defined. The probability of a specific partition is a product of functions of clusters of the partition with the product running over all clusters. This class contains Chinese restaurant processes as a special case. The simulation of a distribution in this class is described through the seating probability that gives the conditional probability of joining a new object to an existing cluster. Examples in Bayesian mixture models are given.\",\"PeriodicalId\":80753,\"journal\":{\"name\":\"Bulletin - Cosmos Club. Cosmos Club (Washington, D.C.)\",\"volume\":\"65 1\",\"pages\":\"107-111\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2005-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bulletin - Cosmos Club. Cosmos Club (Washington, D.C.)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1142/S0219607705000073\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bulletin - Cosmos Club. Cosmos Club (Washington, D.C.)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/S0219607705000073","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A class of distributions on partitions of a finite collection of objects is defined. The probability of a specific partition is a product of functions of clusters of the partition with the product running over all clusters. This class contains Chinese restaurant processes as a special case. The simulation of a distribution in this class is described through the seating probability that gives the conditional probability of joining a new object to an existing cluster. Examples in Bayesian mixture models are given.