Optimal variable selection in multi-group sparse discriminant analysis

Abstract

This article considers the problem of multi-group classification in the setting where the number of variables $p$ is larger than the number of observations $n$. Several methods have been proposed in the literature that address this problem, however their variable selection performance is either unknown or suboptimal to the results known in the two-group case. In this work we provide sharp conditions for the consistent recovery of relevant variables in the multi-group case using the discriminant analysis proposal of Gaynanova et al., 2014. We achieve the rates of convergence that attain the optimal scaling of the sample size $n$, number of variables $p$ and the sparsity level $s$. These rates are significantly faster than the best known results in the multi-group case. Moreover, they coincide with the optimal minimax rates for the two-group case. We validate our theoretical results with numerical analysis.

22 pages, 2 figures

References in corpus (3)

• High-dimensional classification using features annealed independence rules
• Sparse linear discriminant analysis by thresholding for high dimensional data
• Simultaneous sparse estimation of canonical vectors in the p>>N setting

Cited by in corpus (5)

• Sparse quadratic classification rules via linear dimension reduction
• Sparse Generalized Eigenvalue Problem: Optimal Statistical Rates via Truncated Rayleigh Flow
• Joint association and classification analysis of multi-view data
• Interpretable discriminant analysis for functional data supported on random nonlinear domains with an application to Alzheimer's disease
• Variable selection and basis learning for ordinal classification