Robust classification with flexible discriminant analysis in heterogeneous data

Linear and Quadratic Discriminant Analysis are well-known The new method called Generalized QDA (GQDA) classical methods but can heavily suffer from non-Gaussian relies on the estimation of a threshold parameter, whose optimal distributions and/or contaminated datasets, mainly because of value is fixed for each sub-family of distribution. The the underlying Gaussian assumption that is not robust. To fill case c 1 corresponds to the Gaussian case. Finally, [10] improved this gap, this paper presents a new robust discriminant analysis the previous work by adding robust estimators, coming where each data point is drawn by its own arbitrary Elliptically up with the Robust GQDA (RGQDA) method. Symmetrical (ES) distribution and its own arbitrary All these methods assume that all clusters belong to the scale parameter. Such a model allows for possibly very heterogeneous, same distribution family. In practice, such an hypothesis may independent but non-identically distributed samples.