A data driven trimming procedure for robust classification

Marina Agulló Antolín (1) , Eustasio del Barrio (1) , Jean-Michel Loubes (2)

1 UVa - Universidad de Valladolid [Valladolid]
2 IMT - Institut de Mathématiques de Toulouse UMR5219

Classification rules can be severely affected by the presence of disturbing observations in the training sample. Looking for an optimal classifier with such data may lead to unnecessarily complex rules. So, simpler effective classification rules could be achieved if we relax the goal of fitting a good rule for the whole training sample but only consider a fraction of the data. In this paper we introduce a new method based on trimming to produce classification rules with guaranteed performance on a significant fraction of the data. In particular, we provide an automatic way of determining the right trimming proportion and obtain in this setting oracle bounds for the classification error on the new data set.

Mots clés: AMS subject classifications: Primary; 62H10; secondary; 62E20 Keywords: classification; outliers; robust statistics; trimming procedure

Domaines: Statistiques [math.ST]

Marina Agulló Antolín, Eustasio del Barrio, Jean-Michel Loubes. A data driven trimming procedure for robust classification. 2017. ⟨hal-01437147⟩