Parameter-Wise Co-Clustering for High-Dimensional Data - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Computational Statistics Year : 2022

Parameter-Wise Co-Clustering for High-Dimensional Data

Abstract

In recent years, data dimensionality has increasingly become a concern, leading to many parameter and dimension reduction techniques being proposed in the literature. A parameter-wise co-clustering model, for (possibly high-dimensional) data modelled via continuous random variables, is presented. The proposed model, although allowing more flexibility, still maintains the very high degree of parsimony and interpretability achieved by traditional co-clustering. More precisely, the keystone consists of dramatically increasing the number of column-clusters while expressing each as a combination of a limited number of mean-dependent and variance-dependent column-clusters. A stochastic expectation-maximization (SEM) algorithm along with a Gibbs sampler is used for parameter estimation and an integrated complete log-likelihood criterion is used for model selection. Simulated and real datasets are used for illustration and comparison with traditional co-clustering.
Fichier principal
Vignette du fichier
PWCoClust_Revised2.pdf (2.93 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01862824 , version 1 (27-08-2018)
hal-01862824 , version 2 (08-12-2019)
hal-01862824 , version 3 (30-09-2020)
hal-01862824 , version 4 (21-11-2022)

Identifiers

Cite

Michael P B Gallaugher, Christophe Biernacki, Paul D Mcnicholas. Parameter-Wise Co-Clustering for High-Dimensional Data. Computational Statistics, 2022, ⟨10.1007/s00180-022-01289-2⟩. ⟨hal-01862824v4⟩
105 View
97 Download

Altmetric

Share

Gmail Facebook X LinkedIn More