Online k-MLE for Mixture Modeling with Exponential Families

被引:0
|
作者
Saint-Jean, Christophe [1 ]
Nielsen, Frank [2 ]
机构
[1] Univ La Rochelle, MIA, La Rochelle, France
[2] Ecole Polytech, LIX, Palaiseau, France
关键词
Mixture modeling; Online learning; k-MLE; Wishart distribution; CLASSIFICATION EM ALGORITHM;
D O I
10.1007/978-3-319-25040-3_37
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper address the problem of online learning finite statistical mixtures of exponential families. A short review of the Expectation-Maximization (EM) algorithm and its online extensions is done. From these extensions and the description of the k-Maximum Likelihood Estimator (k-MLE), three online extensions are proposed for this latter. To illustrate them, we consider the case of mixtures of Wishart distributions by giving details and providing some experiments.
引用
下载
收藏
页码:340 / 348
页数:9
相关论文
共 50 条
  • [1] K-MLE: A FAST ALGORITHM FOR LEARNING STATISTICAL MIXTURE MODELS
    Nielsen, Frank
    2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 869 - 872
  • [2] On the consistency of MLE in finite mixture models of exponential families
    Atienza, N.
    Garcia-Heras, J.
    Munoz-Pichardo, J. M.
    Villa-Caro, R.
    JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2007, 137 (02) : 496 - 505
  • [3] k-MLE for mixtures of generalized Gaussians
    Schwander, Olivier
    Nielsen, Frank
    Schutz, Aurelien J.
    Berthoumieu, Yannick
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 2825 - 2828
  • [4] MORE COMPARISONS OF MLE WITH UMVUE FOR EXPONENTIAL-FAMILIES
    HWANG, TY
    HU, CY
    ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 1990, 42 (01) : 65 - 75
  • [5] Local mixture models of exponential families
    Anaya-Izquierdo, Karim
    Marriott, Paul
    BERNOULLI, 2007, 13 (03) : 623 - 640
  • [6] Inference on exponential families with mixture of prior distributions
    Rufo, M. J.
    Martin, J.
    Perez, C. J.
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2009, 53 (09) : 3271 - 3280
  • [7] Acoustic Modeling Using Exponential Families
    God, Vaibhava
    Olsen, Peder
    INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1391 - 1394
  • [8] Stochastic complexity for mixture of exponential families in variational Bayes
    Watanabe, K
    Watanabe, S
    ALGORITHMIC LEARNING THEORY, 2005, 3734 : 107 - 121
  • [9] Stochastic complexity for mixture of exponential families in generalized variational Bayes
    Watanabe, Kazuho
    Watanabe, Sumio
    THEORETICAL COMPUTER SCIENCE, 2007, 387 (01) : 4 - 17