期刊文献+

混合逆狄利克雷分布的变分学习及应用 被引量:1

Variational Learning for Finite Inverted Dirichlet Mixture Models and Applications
下载PDF
导出
摘要 混合逆狄利克雷分布是正的非高斯数据分析中一个重要的统计模型.但是利用常用的统计方法比如极大近似然估计、矩估计等往往很难得到模型参数估计的显性解析式.本文提出一个变分贝叶斯学习算法,它能够在估计参数的同时自动确定混合分量数.在合成数据集及实测数据集上的实验结果表明利用变分贝叶斯推理来估计混合逆狄利克雷分布是一种非常有效的方法. Finite inverted Dirichlet mixture models play an important part in positive non-Gaussian data analysis. However, it is always different to obtain the analytical solutions to model parameters by using conventional approaches such as maximization likelihood estimation and moment estimation. In this paper, we have proposed a variational inference framework. Within this frame- work, pm"mneter estimation and automatic model selection can be carried out simulta-neously. Experimental results on synthetic and real-world data sets demonslrate the effectiveness and the merits of the proposed approach.
出处 《电子学报》 EI CAS CSCD 北大核心 2014年第7期1435-1440,共6页 Acta Electronica Sinica
基金 国家自然科学基金(No.61121061 No.60972077 No.61072079 No.61303232 No.61363085) 教育部博士点基金(No.20120005110017) 国家863高技术研究发展计划(No.2009AA01AZ430)
关键词 逆狄利克雷分布 贝叶斯估计 变分推理 拓展分解变分近似 模型选择 inverted Dirichlet distribution Bayesian estimation variational inference extended factorized variational approximation model selection
  • 相关文献

参考文献14

二级参考文献100

  • 1熊刚,赵惠昌,王李军.海杂波背景下雷达引信的相关检测方法研究[J].电子学报,2004,32(12):1937-1940. 被引量:5
  • 2McLachlan G, Peel D. Finite Mixture Models[ M]. New York: John Wiley Sons,2000. 被引量:1
  • 3W K Hastings. Monto Carlo sampling methods using Markov chains and their Applications [ J]. Biometrika, 1970, 57 (1):97 - 109. 被引量:1
  • 4A P Dempster NML,D B Rubin.Maximum likelihood from Incomplete Data via the EM algorithm[ J ]. Journal of the Royal statistical Society, Series B, 1977,39( 1 ) : 1 - 28. 被引量:1
  • 5Constantinos Constantinopoulos, Michalis K. Titsias, and Aristidis Likas, Bayesian Feature and Model Selection for Gaussian Mixture Models[ J] .WEE Transactions of Pattern Analysis and Machine Intelligence, 2006,6 (28) : 1013 - 1018. 被引量:1
  • 6Nizar Bouguila, Djemel Ziou. A Hybrid Sem Algorithm for High-Dimensional Unsupervised Learning Using a Finite Generalized Dirichlet Mixture [ J ]. IEEE Transactions on Image Processing, 2006,15 ( 9 ) : 2657 - 2668. 被引量:1
  • 7Mario A T Figueiredo, Anil K. Jain. Unsupervised Learning of Finite Mixture Models [ J]. IEEE Transactions of Pattern Analysis and Machine Intelligence,2002,3(24) :381 - 396. 被引量:1
  • 8Bouguila N, Ziou D. High-dimensional unsupervised selection and estimation of a finite generalized dirichlet mixture model based on minimum message length [ J]. IEEE Transactions on Pattem Analysis and Machine Intelligence, 2007,29(10) : 1716 - 1731. 被引量:1
  • 9Pemkopf F, Bouchaffra D. Genetic-based EM algorithm for learning Gaussian mixture models [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27 (8) : 1344 - 1348. 被引量:1
  • 10Green P J. Reversible jump Markov chain Monte Carlo computation and Bayesian model determination[ J ]. Biometrika, 1995,82(4) : 711 - 732. 被引量:1

共引文献63

同被引文献1

引证文献1

二级引证文献16

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部