Section: New Results

Axis 1: Gaussian-based visualization of Gaussian and non-Gaussian model-based clustering

Participants : Christophe Biernacki, Vincent Vandewalle.

A generic method is introduced to visualize in a Gaussian-like way, and onto $R^2$, results of Gaussian or non-Gaussian model-based clustering. The key point is to explicitly force a spherical Gaussian mixture visualization to inherit from the within cluster overlap which is present in the initial clustering mixture. The result is a particularly user-friendly draw of the clusters, allowing any practitioner to have a thorough overview of the potentially complex clustering result. An entropic measure allows us to inform of the quality of the drawn overlap, in comparison to the true one in the initial space. The proposed method is illustrated on four real data sets of different types (categorical, mixed, functional and network) and is implemented on the R package ClusVis. This work is now in minor revision for an international journal [54]. It has also led to an invited talk to an international conference [42], and several other invitations (the workshop “Advances in data science for big and complex data” at Université Paris-Dauphine in January and the seminary of the Probability and Statistics team of the University Nice Sophia-Antipolis in November).

This is a joint work with Matthieu Marbac from ENSAI.