{"title":"Learning mixtures of Gaussians","authors":"S. Dasgupta","doi":"10.1109/SFFCS.1999.814639","DOIUrl":null,"url":null,"abstract":"Mixtures of Gaussians are among the most fundamental and widely used statistical models. Current techniques for learning such mixtures from data are local search heuristics with weak performance guarantees. We present the first provably correct algorithm for learning a mixture of Gaussians. This algorithm is very simple and returns the true centers of the Gaussians to within the precision specified by the user with high probability. It runs in time only linear in the dimension of the data and polynomial in the number of Gaussians.","PeriodicalId":385047,"journal":{"name":"40th Annual Symposium on Foundations of Computer Science (Cat. No.99CB37039)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"1999-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"708","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"40th Annual Symposium on Foundations of Computer Science (Cat. No.99CB37039)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SFFCS.1999.814639","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 708
Abstract
Mixtures of Gaussians are among the most fundamental and widely used statistical models. Current techniques for learning such mixtures from data are local search heuristics with weak performance guarantees. We present the first provably correct algorithm for learning a mixture of Gaussians. This algorithm is very simple and returns the true centers of the Gaussians to within the precision specified by the user with high probability. It runs in time only linear in the dimension of the data and polynomial in the number of Gaussians.
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
