Feature screening in large scale cluster analysis

DOI10.1016/J.JMVA.2017.08.001zbMATH Open1490.62150arXiv1701.02857OpenAlexW2591918359MaRDI QIDQ153097FDOQ153097

Authors: Trambak Banerjee, Gourab Mukherjee, Peter Radchenko, Trambak Banerjee, Gourab Mukherjee, Peter Radchenko 

Publication date: September 2017

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Abstract: We propose a novel methodology for feature screening in clustering massive datasets, in which both the number of features and the number of observations can potentially be very large. Taking advantage of a fusion penalization based convex clustering criterion, we propose a very fast screening procedure that efficiently discards non-informative features by first computing a clustering score corresponding to the clustering tree constructed for each feature, and then thresholding the resulting values. We provide theoretical support for our approach by establishing uniform non-asymptotic bounds on the clustering scores of the "noise" features. These bounds imply perfect screening of non-informative features with high probability and are derived via careful analysis of the empirical processes corresponding to the clustering trees that are constructed for each of the features by the associated clustering procedure. Through extensive simulation experiments we compare the performance of our proposed method with other screening approaches, popularly used in cluster analysis, and obtain encouraging results. We demonstrate empirically that our method is applicable to cluster analysis of big datasets arising in single-cell gene expression studies.

Full work available at URL: https://arxiv.org/abs/1701.02857

Recommendations

• A framework for feature selection in clustering
• Clustering High-Dimensional Data via Feature Selection
• A simple method for screening variables before clustering microarray data
• Influential features PCA for high dimensional clustering
• Convex clustering via \(l_1\) fusion penalization

zbMATH Keywords

empirical processeshigh-dimensionalityconvex clusteringmodality detectionnon-asymptotic screening rateRNA-Seq datasingle-cell biology

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to biology and medical sciences; meta analysis (62P10)

Cites Work

• Simultaneous Regression Shrinkage, Variable Selection, and Supervised Clustering of Predictors with OSCAR
• Algorithm AS 136: A K-Means Clustering Algorithm
• An introduction to statistical learning. With applications in R
• A framework for feature selection in clustering
• The elements of statistical learning. Data mining, inference, and prediction
• Weak convergence and empirical processes. With applications to statistics
• Penalized model-based clustering
• Penalized model-based clustering with application to variable selection
• On Using Principal Components Before Separating a Mixture of Two Multivariate Normal Distributions
• Variable Selection for Model-Based High-Dimensional Clustering and Its Application to Microarray Data
• Clustering Objects on Subsets of Attributes (with Discussion)
• Title not available (Why is that?)
• Higher criticism for detecting sparse heterogeneous mixtures.
• Higher criticism thresholding: Optimal feature selection when useful features are rare and weak
• On consistency and sparsity for principal components analysis in high dimensions
• The dip test of unimodality
• Detection and feature selection in sparse mixture models
• Size, power and false discovery rates
• Estimation of a Convex Density Contour in Two Dimensions
• Calibrating the Excess Mass and Dip Tests of Modality
• Title not available (Why is that?)
• Influential features PCA for high dimensional clustering
• Using specially designed exponential families for density estimation
• A simple approach to sparse clustering
• Phase transitions for high dimensional clustering and related problems
• Simultaneous supervised clustering and feature selection over a graph
• Hybrid hierarchical clustering with applications to microarray data
• Title not available (Why is that?)
• Convex clustering via \(l_1\) fusion penalization
• Grouping pursuit through a regularization solution surface
• Using Evidence of Mixed Populations to Select Variables for Clustering Very High-Dimensional Data
• Optimal screening and discovery of sparse signals with applications to multistage high throughput studies

Cited In (2)

• Convex clustering via \(l_1\) fusion penalization
• fusionclust

Uses Software

• AS 136
• sparcl
• COSA
• FABIA
• clusfind
• clusterpath

This page was built for publication: Feature screening in large scale cluster analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q153097)