An empirical comparison of EM, SEM and MCMC performance for problematic Gaussian mixture likelihoods

JOSE G. DIAS; MICHEL WEDEL

首页> 外文期刊>Statistics and computing >An empirical comparison of EM, SEM and MCMC performance for problematic Gaussian mixture likelihoods

【24h】

An empirical comparison of EM, SEM and MCMC performance for problematic Gaussian mixture likelihoods

机译：高斯混合可能性问题的EM，SEM和MCMC性能的经验比较

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

We compare EM, SEM, and MCMC algorithms to estimate the parameters of the Gaussian mixture model. We focus on problems in estimation arising from the likelihood function having a sharp ridge or saddle points. We use both synthetic and empirical data with those features. The comparison includes Bayesian approaches with different prior specifications and various procedures to deal with label switching. Although the solutions provided by these stochastic algorithms are more often degenerate, we conclude that SEM and MCMC may display faster convergence and improve the ability to locate the global maximum of the likelihood function.

机译：我们比较了EM，SEM和MCMC算法，以估计高斯混合模型的参数。我们着重于估计中的问题，这些问题是由具有尖脊或鞍点的似然函数引起的。我们使用具有这些特征的综合数据和经验数据。比较包括具有不同先验规格和各种过程以处理标签切换的贝叶斯方法。尽管这些随机算法提供的解决方案更趋于退化，但我们得出的结论是，SEM和MCMC可能显示出更快的收敛性，并提高了定位似然函数的全局最大值的能力。

著录项

来源
《Statistics and computing》 |2004年第4期|p.323-332|共10页
作者
JOSE G. DIAS; MICHEL WEDEL;
展开▼
作者单位

Department of Quantitative Methods, Instituto Superior de Ciencias do Trabalho e da Empresa -ISCTE, Av. das Forcas Armadas, Lisboa 1649-026, Portugal;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类统计学;
关键词
gaussian mixture models; EM algorithm; SEM algorithm; MCMC; label switching; loss functions; conjugate prior; hierarchical prior;

机译：高斯混合模型;EM算法;SEM算法;MCMC;标签切换;损失函数;共轭先验;分层先验;

相似文献

外文文献
中文文献
专利

1. Performance Degradation Assessment for Bearing Based on Ensemble Empirical Mode Decomposition and Gaussian Mixture Model [J] . Sheng Hong, Baoqing Wang, Guoqi Li, Journal of Vibration and Acoustics . 2014,第6期

机译：基于集合经验模态分解和高斯混合模型的轴承性能退化评估
2. Variable selection in generalized estimating equations via empirical likelihood and Gaussian pseudo-likelihood [J] . Xu Jianwen, Zhang Jiamao, Fu Liya Communications in Statistics . 2019,第3a5期

机译：基于经验似然和高斯拟似然的广义估计方程中的变量选择
3. Variable selection in generalized estimating equations via empirical likelihood and Gaussian pseudo-likelihood [J] . Xu Jianwen, Zhang Jiamao, Fu Liya Communications in Statistics . 2019,第3a5期

机译：通过经验似然和高斯伪可能性的广义估计方程中的变量选择
4. An Effect of Background Population Sample Size on the Performance of a Likelihood Ratio-based Forensic Text Comparison System:A Monte Carlo Simulation with Gaussian Mixture Model [C] . Shunichi Ishihara Australasian Language Technology Association workshop . 2016

机译：背景人群样本量对基于似然比的法医文本比较系统性能的影响：基于高斯混合模型的蒙特卡罗模拟
5. RJMCMC algorithm for multivariate Gaussian mixtures with applications in linear mixed-effects models. [D] . Ho, Kwok Wah. 2005

机译：用于多元高斯混合的RJMCMC算法及其在线性混合效应模型中的应用。
6. Empirical Bayes hierarchical models for regularizing maximum likelihood estimation in the matrix Gaussian Procrustes problem [O] . Douglas L. Theobald, Deborah S. Wuttke 2006

机译：经验贝叶斯分层模型用于正则化矩阵高斯Procrustes问题中的最大似然估计
7. MCMC performance for problematic Gaussian mixture likelihoods [O] . José G. Dias, Michel Wedel 2002

机译：有问题的高斯混合可能性的mCmC性能

An empirical comparison of EM, SEM and MCMC performance for problematic Gaussian mixture likelihoods

摘要

著录项

相似文献

相关主题

期刊订阅