A dynamic EM algorithm for estimating mixture proportions

被引：3
|
作者：
Jorgensen, M [1 ]
机构：
[1] Univ Waikato, Dept Stat, Hamilton, New Zealand
来源：
STATISTICS AND COMPUTING | 1999年 / 9卷 / 04期
关键词：
convergence; finite mixture model; maximum likelihood; sequential estimation;
D O I：
10.1023/A:1008916123610
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
We investigate the use of a dynamic form of the EM algorithm to estimate proportions in finite mixtures of known distributions. We prove a consistency result for this algorithm, which employs only a single EM update for each new observation. Our aim is to demonstrate that the slow convergence rate of the EM algorithm in many applications is of little practical consequence in a situation when data is frequently being updated.
引用
收藏
页码：299 / 302
页数：4
相关论文
共 50 条
  • [41] Finite mixture distributions, sequential likelihood and the EM algorithm
    Arcidiacono, P
    Jones, JB
    ECONOMETRICA, 2003, 71 (03) : 933 - 946
  • [42] Statistical convergence of the EM algorithm on Gaussian mixture models
    Zhao, Ruofei
    Li, Yuanzhi
    Sun, Yuekai
    ELECTRONIC JOURNAL OF STATISTICS, 2020, 14 (01): : 632 - 660
  • [43] An EM-type algorithm for multivariate mixture models
    G. R. Oskrochi
    R. B. Davies
    Statistics and Computing, 1997, 7 : 145 - 151
  • [44] Reinforced EM Algorithm for Clustering with Gaussian Mixture Models
    Tobin, Joshua
    Ho, Chin Pang
    Zhang, Mimi
    PROCEEDINGS OF THE 2023 SIAM INTERNATIONAL CONFERENCE ON DATA MINING, SDM, 2023, : 118 - 126
  • [45] An online classification EM algorithm based on the mixture model
    Allou Samé
    Christophe Ambroise
    Gérard Govaert
    Statistics and Computing, 2007, 17 : 209 - 218
  • [46] An online classification EM algorithm based on the mixture model
    Same, Allou
    Ambroise, Christophe
    Govaert, Gerard
    STATISTICS AND COMPUTING, 2007, 17 (03) : 209 - 218
  • [47] EM algorithm with split and merge operations for mixture models
    Ueda, Naonori
    Nakano, Ryohei
    IEICE Transactions on Information and Systems, 2000, E83-D (12) : 2047 - 2055
  • [48] A Single Loop EM Algorithm for the Mixture of Experts Architecture
    Yang, Yan
    Ma, Jinwen
    ADVANCES IN NEURAL NETWORKS - ISNN 2009, PT 2, PROCEEDINGS, 2009, 5552 : 959 - 968
  • [49] LBGU-EM algorithm for mixture density estimation
    Iswanto, BH
    Fritzke, B
    BETWEEN DATA SCIENCE AND APPLIED DATA ANALYSIS, 2003, : 252 - 260
  • [50] EM algorithm with split and merge operations for mixture models
    Ueda, N
    Nakano, R
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2000, E83D (12): : 2047 - 2055
12345