Effective PCA for high-dimension, low-sample-size data with noise reduction via geometric representations

DOI10.1016/J.JMVA.2011.09.002MaRDI QIDQ764487zbMATH OpenOpenAlexFDO

Authors Kazuyoshi Yata, Makoto Aoshima

Publication date 13 March 2012

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

Full work available at URL https://arxiv.org/abs/1503.04525

zbMATH Keywords

consistencydiscriminant analysiseigenvalue distributionHDLSSinverse matrixnoise reductionprincipal components analysis

Mathematics Subject Classification ID

Eigenvalues, singular values, and eigenvectors (15A18) Set-valued maps in general topology (54C60) Asymptotic distribution theory in statistics (62E20) Estimation in multivariate analysis (62H12) Factor analysis and principal components; correspondence analysis (62H25) Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Abstract: In this paper, we consider clustering based on principal component analysis (PCA) for high-dimension, low-sample-size (HDLSS) data. We give theoretical reasons why PCA is effective for clustering HDLSS data. First, we derive a geometric representation of HDLSS data taken from a two-class mixture model. With the help of the geometric representation, we give geometric consistency properties of sample principal component scores in the HDLSS context. We develop ideas of the geometric representation and geometric consistency properties to multiclass mixture models. We show that PCA can classify HDLSS data under certain conditions in a surprisingly explicit way. Finally, we demonstrate the performance of the clustering by using microarray data sets.

Recommendations

• Effective PCA for high-dimension, low-sample-size data with singular value decomposition of cross data matrix
• Statistical inference for high-dimension, low-sample-size data
• PCA consistency in high dimension, low sample size context
• Effective methodologies for high-dimensional data
• Boundary behavior in high dimension, low sample size asymptotics of PCA

Cites work

• Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
• Basic properties of strong mixing conditions. A survey and some open questions
• Comparison of Discrimination Methods for High Dimensional Data
• Convergence and prediction of principal component scores in high-dimensional settings
• Effective PCA for high-dimension, low-sample-size data with singular value decomposition of cross data matrix
• Eigenvalues of large sample covariance matrices of spiked population models
• Geometric Representation of High Dimension, Low Sample Size Data
• Intrinsic dimensionality estimation of high-dimension, low sample size data with \(D\)-asymptotics
• Minimum distance classification rules for high dimensional data
• Multivariate Theory for Analyzing High Dimensional Data
• On Strong Mixing Conditions for Stationary Gaussian Processes
• On the distribution of the largest eigenvalue in principal components analysis
• PCA Consistency for Non-Gaussian Data in High Dimension, Low Sample Size Context
• PCA consistency in high dimension, low sample size context
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• The high-dimension, low-sample-size geometric representation holds under mild conditions

Cited in

(93)

• Inference on high-dimensional mean vectors with fewer observations than the dimension
• Distance-based classifier by data transformation for high-dimension, strongly spiked eigenvalue models
• Hypothesis tests for high-dimensional covariance structures
• Clustering by principal component analysis with Gaussian kernel in high-dimension, low-sample-size settings
• Geometric classifiers for high-dimensional noisy data
• Double data piling leads to perfect classification
• Consistency of the objective general index in high-dimensional settings
• More about asymptotic properties of some binary classification methods for high dimensional data
• Asymptotic independence of spiked eigenvalues and linear spectral statistics for large sample covariance matrices
• Perturbation theory for cross data matrix-based PCA
• Limiting laws for divergent spiked eigenvalues and largest nonspiked eigenvalue of sample covariance matrices
• Two-stage dimension reduction for noisy high-dimensional images and application to cryogenic electron microscopy
• On asymptotic normality of cross data matrix-based PCA in high dimension low sample size
• Equality tests of high-dimensional covariance matrices under the strongly spiked eigenvalue model
• Location-invariant tests of homogeneity of large-dimensional covariance matrices
• Inference on high-dimensional mean vectors under the strongly spiked eigenvalue model
• Using visual statistical inference to better understand random class separations in high dimension, low sample size data
• Semiparametric estimation of the high-dimensional elliptical distribution
• Reconstruction of a high-dimensional low-rank matrix
• Overview of object oriented data analysis
• Two-stage procedures for high-dimensional data
• Authors' response
• Analysis of high-dimensional one group repeated measures designs
• Intrinsic dimensionality estimation of high-dimension, low sample size data with \(D\)-asymptotics
• Correlation tests for high-dimensional data using extended cross-data-matrix methodology
• Reconstruction of a low-rank matrix in the presence of Gaussian noise
• Asymptotics of hierarchical clustering for growing dimension
• Statistical inference for high-dimension, low-sample-size data
• A High-Dimensional Two-Sample Test for Non-Gaussian Data under a Strongly Spiked Eigenvalue Model
• A test of sphericity for high-dimensional data and its application for detection of divergently spiked noise
• A survey of high dimension low sample size asymptotics
• scientific article; zbMATH DE number 7376764 (Why is no real title available?)
• scientific article; zbMATH DE number 7387552 (Why is no real title available?)
• A classifier under the strongly spiked eigenvalue model in high-dimension, low-sample-size context
• Binary discrimination methods for high-dimensional data with a geometric representation
• On estimation of the noise variance in high dimensional probabilistic principal component analysis
• Discussion on ``Two-stage procedures for high-dimensional data by Makoto Aoshima and Kazuyoshi Yata
• Robust PCA for high‐dimensional data based on characteristic transformation
• CORRELATION MATRIX OF EQUI-CORRELATED NORMAL POPULATION: FLUCTUATION OF THE LARGEST EIGENVALUE, SCALING OF THE BULK EIGENVALUES, AND STOCK MARKET
• High-dimensional hypothesis testing for allometric extension model
• Polynomial whitening for high-dimensional data
• Effective methodologies for high-dimensional data
• Statistical inference under the strongly spiked eigenvalue model
• Equality tests of covariance matrices under a low-dimensional factor structure
• Test for high-dimensional outliers with principal component analysis
• Automatic sparse estimation of the high-dimensional cross-covariance matrix
• Low dimensional factor model-based tests for assessing vector correlation in high-dimensional settings
• Asymptotic behavior of some multicategory classification methods for high-dimensional data
• High-Dimensional Block Diagonal Covariance Structure Detection Using Singular Vectors
• Estimators for multivariate allometric regression model
• High-dimensional behaviour of some two-sample tests based on ball divergence
• Automatic sparse PCA for high-dimensional data
• Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Reply to the discussion of: ``Statistical exploration of the manifold hypothesis
• Statistical hypothesis testing for high-dimension, low-sample-size data
• A variance-corrected U-statistic approach for comparing covariance matrices of high-dimensional mixtures
• Correlation tests for high-dimensional data under the strongly spiked eigenvalue model
• A general framework for testing clustering significance and variable-level inference in high-dimensional data
• A distance-based, misclassification rate adjusted classifier for multiclass, high-dimensional data
• Estimation of linear functional of large spectral density matrix and application to Whittle's approach
• Asymptotic properties of the first principal component and equality tests of covariance matrices in high-dimension, low-sample-size context
• Effective PCA for high-dimension, low-sample-size data with singular value decomposition of cross data matrix

This page was built for publication: Effective PCA for high-dimension, low-sample-size data with noise reduction via geometric representations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q764487)