Pitfalls in Mixtures from the Clustering Angle

Christophe Biernacki; Gwenaelle Castellan; Stephane Chretien; Benjamin Guedj; Vincent Vandewalle

Conference papers

Pitfalls in Mixtures from the Clustering Angle

Christophe Biernacki ^{1, 2} Gwenaelle Castellan ² Stephane Chretien ³ Benjamin Guedj ¹ Vincent Vandewalle ^{1, 4}

1 MODAL - MOdel for Data Analysis and Learning

Inria Lille - Nord Europe, LPP - Laboratoire Paul Painlevé - UMR 8524, METRICS - Evaluation des technologies de santé et des pratiques médicales - ULR 2694, Polytech Lille - École polytechnique universitaire de Lille, Université de Lille, Sciences et Technologies

2 LPP - Laboratoire Paul Painlevé - UMR 8524

3 NPL - National Physical Laboratory [Teddington]

4 METRICS - Evaluation des technologies de santé et des pratiques médicales - ULR 2694

Abstract : Slides of this talk are both a review and a prospective work about degeneracy, label switching and spurious in a model-based clustering context. Originality is to deal with these topics from a dynamical point of view on the EM algorithm, and other related algorithms.

Keywords : Model-based clustering Label switching Spurious attractors Degeneracy

Document type :

Conference papers

Domain :

Statistics [stat] / Methodology [stat.ME]

Complete list of metadata

https://hal.archives-ouvertes.fr/hal-01419755
Contributor : Christophe Biernacki <>
Submitted on : Wednesday, December 21, 2016 - 5:40:10 PM
Last modification on : Friday, November 27, 2020 - 2:18:02 PM

Pitfalls in Mixtures from the Clustering Angle

Annex

Identifiers

Collections

Citation

Export

Metrics

340

44

Pitfalls in Mixtures from the Clustering Angle

Annex

Identifiers

Collections

Citation

Export

Share

Metrics

340

44