scholarly journals Model-based clustering of high-dimensional data: A review

2014 ◽  
Vol 71 ◽  
pp. 52-78 ◽  
Author(s):  
Charles Bouveyron ◽  
Camille Brunet-Saumard
Keyword(s):  
High Dimensional Data ◽  
High Dimensional ◽  
Model Based Clustering ◽  
Model Based

scholarly journals Model-based clustering of high-dimensional data streams with online mixture of probabilistic PCA

2013 ◽  
Vol 7 (3) ◽  
pp. 281-300 ◽  
Author(s):  
Anastasios Bellas ◽  
Charles Bouveyron ◽  
Marie Cottrell ◽  
Jérôme Lacaille
Keyword(s):  
Data Streams ◽  
High Dimensional Data ◽  
High Dimensional ◽  
Model Based Clustering ◽  
Probabilistic Pca ◽  
Model Based

scholarly journals Model-based Clustering using Automatic Differentiation: Confronting Misspecification and High-Dimensional Data

2019 ◽  
Author(s):  
Siva Rajesh Kasa ◽  
Vaibhav Rajan
Keyword(s):  
Automatic Differentiation ◽  
High Dimensional Data ◽  
Penalized Likelihood ◽  
Gaussian Mixture ◽  
High Dimensional ◽  
Adjusted Rand Index ◽  
Penalty Term ◽  
Model Based Clustering ◽  
Model Based ◽  
Leibler Divergence

AbstractWe study two practically important cases of model based clustering using Gaussian Mixture Models: (1) when there is misspecification and (2) on high dimensional data, in the light of recent advances in Gradient Descent (GD) based optimization using Automatic Differentiation (AD). Our simulation studies show that EM has better clustering performance, measured by Adjusted Rand Index, compared to GD in cases of misspecification, whereas on high dimensional data GD outperforms EM. We observe that both with EM and GD there are many solutions with high likelihood but poor cluster interpretation. To address this problem we design a new penalty term for the likelihood based on the Kullback Leibler divergence between pairs of fitted components. Closed form expressions for the gradients of this penalized likelihood are difficult to derive but AD can be done effortlessly, illustrating the advantage of AD-based optimization. Extensions of this penalty for high dimensional data and for model selection are discussed. Numerical experiments on synthetic and real datasets demonstrate the efficacy of clustering using the proposed penalized likelihood approach.

scholarly journals Model-based clustering of high-dimensional data: Variable selection versus facet determination

2013 ◽  
Vol 54 (1) ◽  
pp. 196-215 ◽  
Author(s):  
Leonard K.M. Poon ◽  
Nevin L. Zhang ◽  
Tengfei Liu ◽  
April H. Liu
Keyword(s):  
Variable Selection ◽  
High Dimensional Data ◽  
High Dimensional ◽  
Model Based Clustering ◽  
Model Based

scholarly journals Pairwise Variable Selection for High-Dimensional Model-Based Clustering

Biometrics ◽  
2009 ◽  
Vol 66 (3) ◽  
pp. 793-804 ◽  
Author(s):  
Jian Guo ◽  
Elizaveta Levina ◽  
George Michailidis ◽  
Ji Zhu
Keyword(s):  
Variable Selection ◽  
High Dimensional ◽  
Dimensional Model ◽  
Model Based Clustering ◽  
Model Based ◽  
Selection For
Sign in / Sign up

Export Citation Format

Share Document