High Dimensional Linear Discriminant Analysis: Optimality, Adaptive Algorithm and Missing Data

DOI10.1111/RSSB.12326MaRDI QIDQ5204360zbMATH OpenOpenAlexWikidataFDO

Authors Linjun Zhang, T. Tony Cai

Publication date 4 December 2019

Published in Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1804.03018

zbMATH Keywords

adaptive classification ruleconstrained \(l_1\)-minimizationhigh dimensional datalinear discriminant analysismissing dataoptimal rate of convergence

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to biology and medical sciences; meta analysis (62P10)

Abstract: This paper aims to develop an optimality theory for linear discriminant analysis in the high-dimensional setting. A data-driven and tuning free classification rule, which is based on an adaptive constrained $el{l}_1$ minimization approach, is proposed and analyzed. Minimax lower bounds are obtained and this classification rule is shown to be simultaneously rate optimal over a collection of parameter spaces. In addition, we consider classification with incomplete data under the missing completely at random (MCR) model. An adaptive classifier with theoretical guarantees is introduced and optimal rate of convergence for high-dimensional linear discriminant analysis under the MCR model is established. The technical analysis for the case of missing data is much more challenging than that for the complete data. We establish a large deviation result for the generalized sample covariance matrix, which serves as a key technical tool and can be of independent interest. An application to lung cancer and leukemia studies is also discussed.

Recommendations

• High-dimensional linear discriminant analysis using nonparametric methods
• A modified linear discriminant analysis for high-dimensional data
• Dynamic linear discriminant analysis in high dimensional space
• Optimal discriminant analysis in high-dimensional latent factor models
• High-Dimensional Discriminant Analysis
• Sparse linear discriminant analysis with applications to high dimensional low sample size data
• An Efficient Greedy Search Algorithm for High-Dimensional Linear Discriminant Analysis
• A variable selection criterion for linear discriminant rule and its optimality in high dimensional and large sample data
• An adapted linear discriminant analysis with variable selection for the classification in high-dimension, and an application to medical data
• On sparse linear discriminant analysis algorithm for high-dimensional data classification.

Cited in

(32)

• Varying coefficient linear discriminant analysis for dynamic data
• Optimal functional supervised classification with separation condition
• Dynamic linear discriminant analysis in high dimensional space
• Fast rate of convergence in high-dimensional linear discriminant analysis
• Integrative linear discriminant analysis with guaranteed error rate improvement
• High-dimensional linear discriminant analysis classifier for spiked covariance model
• A Sparse Learning Approach to Relative-Volatility-Managed Portfolio Selection
• scientific article; zbMATH DE number 7370646 (Why is no real title available?)
• scientific article; zbMATH DE number 7625194 (Why is no real title available?)
• Nonparametric discriminant analysis with network structures in predictor
• Optimal discriminant analysis in high-dimensional latent factor models
• Deep neural network classifier for multidimensional functional data
• Optimal nonparametric testing of missing completely at random and its connections to compatibility
• Multiclass sparse discriminant analysis incorporating graphical structure among predictors
• Multiclass classification for multidimensional functional data through deep neural networks
• Optimal Linear Discriminant Analysis for High-Dimensional Functional Data
• Optimal classification for functional data
• Nonparametric classification with missing data
• Spectral analysis of Gram matrices with missing at random observations: convergence, central limit theorems, and applications in statistical inference
• A locally adaptive shrinkage approach to false selection rate control in high-dimensional classification
• ATM: an aggregation test of moments approach for assessing high-dimensional normality
• Unsupervised linear discrimination using skewness
• Tests of missing completely at random based on sample covariance matrices
• High-dimensional scale invariant discriminant analysis
• High dimensional discriminant analysis under weak sparsity
• Local multi-scale structure discriminant analysis
• Sharp-SSL: Selective High-Dimensional Axis-Aligned Random Projections for Semi-Supervised Learning
• Non-splitting Neyman-Pearson classifiers
• Sparse robust discriminant analysis for high-dimensional and heavy-tailed data
• Estimation beyond missing (completely) at random
• A convex optimization approach to high-dimensional sparse quadratic discriminant analysis
• A self-calibrated direct approach to precision matrix estimation and linear discriminant analysis in high dimensions

This page was built for publication: High Dimensional Linear Discriminant Analysis: Optimality, Adaptive Algorithm and Missing Data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5204360)