Variational learning for finite Beta-Liouville mixture models  

作　　者：LAI Yu-ping ZHOU Ya-jian PING Yuan GUO Yu-cui YANG Yi-xian 

机构地区：[1]Information Security Center, Beijing University of Posts and Telecommunications [2]Department of Computer Science and Technology, Xuchang University [3]School of Science, Beijing University of Posts and Telecommunications

出　　处：《The Journal of China Universities of Posts and Telecommunications》2014年第2期98-103,共6页中国邮电高校学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(61303232,61363085,61121061,60972077);the Hi-Tech Research and Development Program of China(2009AA01Z430)

摘　　要：In the article, an improved variational inference （VI） framework for learning finite Beta-Liouville mixture models （BLM） is proposed for proportional data classification and clustering. Within the VI framework, some non-linear approximation techniques are adopted to obtain the approximated variational object functions. Analytical solutions are obtained for the variational posterior distributions. Compared to the expectation maximization （EM） algorithm which is commonly used for learning mixture models, underfitting and overfitting events can be prevented. Furthermore, parameters and complexity of the mixture model （model order） can be estimated simultaneously. Experiment shows that both synthetic and real-world data sets are to demonstrate the feasibility and advantages of the proposed method.In the article, an improved variational inference （VI） framework for learning finite Beta-Liouville mixture models （BLM） is proposed for proportional data classification and clustering. Within the VI framework, some non-linear approximation techniques are adopted to obtain the approximated variational object functions. Analytical solutions are obtained for the variational posterior distributions. Compared to the expectation maximization （EM） algorithm which is commonly used for learning mixture models, underfitting and overfitting events can be prevented. Furthermore, parameters and complexity of the mixture model （model order） can be estimated simultaneously. Experiment shows that both synthetic and real-world data sets are to demonstrate the feasibility and advantages of the proposed method.

关 键 词：variational inference model selection factorized approximation Beta-Liouville distribution mixing modeling 

分 类 号：O176[理学—数学]