Avoiding spurious local maximizers in mixture modeling

Garcia-Escudero L. A.; Gordaliza A.; Matran C.; Mayo-Iscar A.

首页> 外文期刊>Statistics and computing >Avoiding spurious local maximizers in mixture modeling

【24h】

Avoiding spurious local maximizers in mixture modeling

机译：在混合模型中避免伪局部最大化器

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

The maximum likelihood estimation in the finite mixture of distributions setting is an ill-posed problem that is treatable, in practice, through the EM algorithm. However, the existence of spurious solutions (singularities and non-interesting local maximizers) makes difficult to find sensible mixture fits for non-expert practitioners. In this work, a constrained mixture fitting approach is presented with the aim of overcoming the troubles introduced by spurious solutions. Sound mathematical support is provided and, which is more relevant in practice, a feasible algorithm is also given. This algorithm allows for monitoring solutions in terms of the constant involved in the restrictions, which yields a natural way to discard spurious solutions and a valuable tool for data analysts.

机译：分布的有限混合设置中的最大似然估计是一个不适定问题，实际上可以通过EM算法解决。但是，存在虚假解（奇异性和不感兴趣的局部最大化器）使得难以找到适合非专家从业者的明智混合。在这项工作中，提出了一种受约束的混合拟合方法，其目的是克服由虚假解决方案引入的麻烦。提供了可靠的数学支持，并且在实践中更有意义，并且给出了可行的算法。该算法允许根据限制中涉及的常数来监视解决方案，这为丢弃伪造的解决方案提供了一种自然的方法，并为数据分析人员提供了一种有价值的工具。

著录项

来源
《Statistics and computing》 |2015年第3期|619-633|共15页
作者
Garcia-Escudero L. A.; Gordaliza A.; Matran C.; Mayo-Iscar A.;
展开▼
作者单位

Univ Valladolid, IMUVA, E-47011 Valladolid, Spain|Univ Valladolid, Dept Estadist & Invest Operat, Fac Ciencias, E-47011 Valladolid, Spain;

Univ Valladolid, IMUVA, E-47011 Valladolid, Spain|Univ Valladolid, Dept Estadist & Invest Operat, Fac Ciencias, E-47011 Valladolid, Spain;

Univ Valladolid, IMUVA, E-47011 Valladolid, Spain|Univ Valladolid, Dept Estadist & Invest Operat, Fac Ciencias, E-47011 Valladolid, Spain;

Univ Valladolid, IMUVA, E-47011 Valladolid, Spain|Univ Valladolid, Dept Estadist & Invest Operat, Fac Ciencias, E-47011 Valladolid, Spain;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Mixtures; Maximum likelihood; EM algorithm; Eigenvalues constraints;

机译：混合物;最大似然;EM算法;特征值约束;

相似文献

外文文献
中文文献
专利

1. A constrained robust proposal for mixture modeling avoiding spurious solutions [J] . L. A. García-Escudero, A. Gordaliza, A. Mayo-Iscar Advances in data analysis and classification . 2014,第1期

机译：混合建模的受约束的健壮建议，避免了假的解
2. A Quantitative Trait Locus Mixture Model That Avoids Spurious LOD Score Peaks [J] . Bjarke Feenstra, Ib M. Skovgaard Genetics: A Periodical Record of Investigations Bearing on Heredity and Variation . 2004,第2期

机译：避免伪造的LOD得分峰值的定量性状基因座混合模型
3. Assessment of the number of components in Gaussian mixture models in the presence of multiple local maximizers [J] . Daeyoung Kim, Byungtae Seo Journal of Multivariate Analysis: An International Journal . 2014,第Null期

机译：在存在多个局部最大化器的情况下评估高斯混合模型中的分量数
4. Learning Gaussian Mixture Model with a Maximization-Maximization Algorithm for Image Classification [C] . Kart-Leong Lim, Han Wang, Xiaozheng Mou IEEE International Conference on Control and Automation . 2016

机译：用最大化最大化算法学习高斯混合模型进行图像分类
5. Enhancing Prediction Efficacy with High-Dimensional Input via Structural Mixture Modeling of Local Linear Mappings [D] . Tu, Chun-Chen 2019

机译：通过局部线性映射的结构混合建模，通过高维输入增强预测功效
6. A quantitative trait locus mixture model that avoids spurious LOD score peaks. [O] . Bjarke Feenstra, Ib M Skovgaard 2004

机译：避免杂散LOD得分峰值的定量性状基因座混合模型。
7. Avoiding Spurious Local Maximizers in Mixture Modeling [O] . García Escudero Luis Angel, Gordaliza Ramos Alfonso, Matrán Bea Carlos, 2014

机译：在混合建模中避免虚假的局部最大化器

Avoiding spurious local maximizers in mixture modeling

摘要

著录项

相似文献

相关主题

期刊订阅