Journal Article10.1016/J.CSDA.2009.04.012
Learning mixture models via component-wise parameter smoothing
Chandan K. Reddy,Bala Rajaratnam +1 more
TL;DR: A novel algorithm using a convolution based smoothing approach to construct a hierarchy (or family) of smoothed log-likelihood surfaces is proposed, which effectively eliminates extensive searching in non-promising regions of the parameter space.
read more
About: This article is published in Computational Statistics & Data Analysis. The article was published on 01 Mar 2010. The article focuses on the topics: Smoothing & Expectation–maximization algorithm.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Vertebral body segmentation using a probabilistic and universal shape model
TL;DR: The authors' objective is to segment the VBs as accurately as possible and hence to increase the accuracy of the BMD measurements and fracture analysis and the proposed framework is robust under various noise levels, less variant to the initialisation and faster than existing vertebrae segmentation reports in the literature.
10
Comparison of methods for initializing EM algorithm for estimation of parameters of Gaussian, multi-component, heteroscedastic mixture models
Radosław Sokół,Andrzej Polański +1 more
- 09 Feb 2013
TL;DR: This paper presents several different initial condition estimation methods, which may be used as a first step in the EM parameter estimation procedure for heteroscedastic, multi-component Gaussian mixtures.
5
Dealing with multiple local modalities in latent class profile analysis
Hsiu-Ching Chang,Hwan Chung +1 more
TL;DR: Two probabilistic optimization techniques using the deterministic annealing framework are proposed to deal with multiple local modalities in the latent class profile analysis (LCPA) model.
5
Robust mixture model cluster analysis using adaptive kernels
TL;DR: This work adapts two computational algorithms, genetic algorithm with regularized Mahalanobis distance and genetic expectation maximization algorithm, to optimize the kernel mixture model (KMM) and uses results from robust estimation theory in order to data-adaptively regularize both.
4
References
•Book
The EM algorithm and extensions
Geoffrey J. McLachlan,Thriyambakam Krishnan +1 more
- 15 Nov 1996
TL;DR: The EM Algorithm and Extensions describes the formulation of the EM algorithm, details its methodology, discusses its implementation, and illustrates applications in many statistical contexts, opening the door to the tremendous potential of this remarkably versatile statistical tool.
A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs
George Karypis,Vipin Kumar +1 more
TL;DR: This work presents a new coarsening heuristic (called heavy-edge heuristic) for which the size of the partition of the coarse graph is within a small factor of theSize of the final partition obtained after multilevel refinement, and presents a much faster variation of the Kernighan--Lin (KL) algorithm for refining during uncoarsening.
Text Classification from Labeled and Unlabeled Documents using EM
TL;DR: This paper shows that the accuracy of learned text classifiers can be improved by augmenting a small number of labeled training documents with a large pool of unlabeled documents, and presents two extensions to the algorithm that improve classification accuracy under these conditions.