A note on EM algorithm for mixture models

被引：28

作者：

Yao, Weixin ^{[1
]}

机构：

[1] Kansas State Univ, Dept Stat, Manhattan, KS 66506 USA

来源：

STATISTICS & PROBABILITY LETTERS | 2013年 / 83卷 / 02期

关键词：

Adaptive regression; EM algorithm; Edge-preserving smoothers; Mode; Robust regression; LIKELIHOOD; REGRESSION;

D O I：

10.1016/j.spl.2012.10.017

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Expectation-maximization (EM) algorithm has been used to maximize the likelihood function or posterior when the model contains unobserved latent variables. One main important application of EM algorithm is to find the maximum likelihood estimator for mixture models. In this article, we propose an EM type algorithm to maximize a class of mixture type objective functions. In addition, we prove the monotone ascending property of the proposed algorithm and discuss some of its applications. (c) 2012 Elsevier B.V. All rights reserved.

引用

页码：519 / 526

页数：8

共 50 条

[41] On-line EM algorithm for mixture of local experts [J].

Sato, M ;

Ishii, S .

ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, :1397-1401

[42] Finite mixture distributions, sequential likelihood and the EM algorithm [J].

Arcidiacono, P ;

Jones, JB .

ECONOMETRICA, 2003, 71 (03) :933-946

[43] An EM algorithm for estimation in the mixture transition distribution model [J].

Lebre, Sophie ;

Bourguignon, Pierre-Yves .

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2008, 78 (08) :713-729

[44] Genetic-based EM algorithm to improve the robustness of Gaussian mixture models for damage detection in bridges [J].

Santos, Adam ;

Figueiredo, Eloi ;

Silva, Moises ;

Santos, Reginaldo ;

Sales, Claudomiro ;

Costa, Joao C. W. A. .

STRUCTURAL CONTROL & HEALTH MONITORING, 2017, 24 (03)

[45] Alternative EM methods for nonparametric finite mixture models [J].

Pilla, RS ;

Lindsay, BG .

BIOMETRIKA, 2001, 88 (02) :535-550

[46] A Thresholding Algorithm for Order Selection in Finite Mixture Models [J].

Xu, Chen ;

Chen, Jiahua .

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2015, 44 (02) :433-453

[47] Bayesian Estimation for {ij}-Inflated Mixture Power Series Distributions using an EM Algorithm [J].

Najafabadi, Amir T. Payandeh ;

Sakizadeh, Mansoureh .

THAILAND STATISTICIAN, 2025, 23 (03) :460-480

[48] Asymptotic convergence properties of the EM algorithm with respect to the overlap in the mixture [J].

Ma, JW ;

Xu, L .

NEUROCOMPUTING, 2005, 68 :105-129

[49] A distributed EM algorithm to estimate the parameters of a finite mixture of components [J].

Safarinejadian, Behrooz ;

Menhaj, Mohammad B. ;

Karrari, Mehdi .

KNOWLEDGE AND INFORMATION SYSTEMS, 2010, 23 (03) :267-292

[50] Using the EM-algorithm to Approximate the Distribution of a Mixture by Hyperexponents [J].

Buranova, Marina ;

Ergasheva, Dinara ;

Kartashevskiy, Vyacheslav .

2019 INTERNATIONAL CONFERENCE ON ENGINEERING AND TELECOMMUNICATION (ENT), 2019,

← 1 2 3 4 5 →