Penalized Model-Based Clustering with Application to Variable Selection

By Wei Pan, Xiaotong Shen. Journal of machine learning research, 2007

316 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b640168f39aaf8f19d9fd86ee9dea5accea04dc5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Statistical Significance of Clustering for High-Dimension, Low–Sample Size Data (2008, methodology): “Recently proposed clustering methods include those of Tseng and Wong (2005) and Pan and Shen (2007).”
A Framework for Feature Selection in Clustering (2010, methodology): “This approach is taken in a number of papers, including Pan and Shen (2007), Wang and Zhu (2008), and Xie, Pan, and Shen (2008).”
A review on particle swarm optimization algorithm and its variants to clustering high-dimensional data (2013, methodology): “1998; Chan and Hall 2010; Raftery and Dean 2006), model-based methods such as (Pan and Shen 2007; Wang ans Zhu 2008), and criterion-based methods such as (Witten and Tibshirani 2010; Raftery and Dean 2006).”
Model-based clustering of high-dimensional data: A review (2014, methodology): “In GMM context, Pan & Shen [78] proposed a penalized log-likelihood criterion by assuming a Gaussian mixture model with common diagonal covariance matrices, meaning that ∀ k ∈ { 1 , . . . , K } , The penalty function is focused on the means of K clusters ( m 1 k , . . . , m pk , ∀ k ∈ { 1 , . . . , ”
Regularized k-means clustering of high-dimensional data and its asymptotic consistency (2012, background): “To facilitate the high-dimensional clustering as in [16], we further assume that a common diagonal covariance matrix is shared among the mixture components.”
Finite mixture models and model-based clustering (2010, methodology): “For model selection, [97] extended the penalized loglikelihood-based variable selection procedure of [96] to the context of model-based semi-supervised clustering for gene expression data, but their approach was limited by the assumption of uncorrelated variables.”
ℓ1-penalization for mixture regression models (2010, background): “,k 1{φ̂r,j 6=0} is the effective number of parameters (Pan and Shen, 2007).”
Multiple predicting K-fold cross-validation for model selection (2018, methodology): “Some examples include the suggestions by Chen and Chen (2008) and Chen and Chen (2012) under linear and generalised linear model, respectively, and by Pan and Shen (2007) under model-based clustering.”