English

Optimal variable selection in multi-group sparse discriminant analysis

Machine Learning 2021-04-01 v1

Abstract

This article considers the problem of multi-group classification in the setting where the number of variables pp is larger than the number of observations nn. 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 nn, number of variables pp and the sparsity level ss. 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.

Keywords

Cite

@article{arxiv.1411.6311,
  title  = {Optimal variable selection in multi-group sparse discriminant analysis},
  author = {Irina Gaynanova and Mladen Kolar},
  journal= {arXiv preprint arXiv:1411.6311},
  year   = {2021}
}

Comments

22 pages, 2 figures

R2 v1 2026-06-22T07:09:14.323Z