English

Robust classification with flexible discriminant analysis in heterogeneous data

Machine Learning 2022-01-11 v1 Machine Learning Applications

Abstract

Linear and Quadratic Discriminant Analysis are well-known classical methods but can heavily suffer from non-Gaussian distributions and/or contaminated datasets, mainly because of the underlying Gaussian assumption that is not robust. To fill this gap, this paper presents a new robust discriminant analysis where each data point is drawn by its own arbitrary Elliptically Symmetrical (ES) distribution and its own arbitrary scale parameter. Such a model allows for possibly very heterogeneous, independent but non-identically distributed samples. After deriving a new decision rule, it is shown that maximum-likelihood parameter estimation and classification are very simple, fast and robust compared to state-of-the-art methods.

Keywords

Cite

@article{arxiv.2201.02967,
  title  = {Robust classification with flexible discriminant analysis in heterogeneous data},
  author = {Pierre Houdouin and Frédéric Pascal and Matthieu Jonckheere and Andrew Wang},
  journal= {arXiv preprint arXiv:2201.02967},
  year   = {2022}
}

Comments

ICASSP conference paper, 5 pages

R2 v1 2026-06-24T08:43:59.222Z