Skip to Main content Skip to Navigation
Conference papers

Bayesian mixtures of multiple scale distributions

Florence Forbes 1 Alexis Arnaud 1 Russell Steele 2 Benjamin Lemasson 3 Emmanuel Barbier 4
1 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP [2007-2019] - Institut polytechnique de Grenoble - Grenoble Institute of Technology [2007-2019]
Abstract : Multiple scale distributions are multivariate distributions that exhibit a variety of shapes not necessarily elliptical while remaining analytical and tractable. In this work we consider mixtures of such distributions for their ability to handle non standard typically non-gaussian clustering tasks. We propose a Bayesian formulation of the mixtures and a tractable inference procedure based on variational approximation. The interest of such a Bayesian formulation is illustrated on an important mixture model selection task, which is the issue of selecting automatically the number of components. We derive promising procedures that can be carried out in a single-run, in contrast to the more costly comparison of information criteria.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01941682
Contributor : Florence Forbes <>
Submitted on : Monday, December 3, 2018 - 10:52:46 AM
Last modification on : Thursday, July 9, 2020 - 9:44:39 AM

Identifiers

  • HAL Id : hal-01941682, version 1

Collections

Citation

Florence Forbes, Alexis Arnaud, Russell Steele, Benjamin Lemasson, Emmanuel Barbier. Bayesian mixtures of multiple scale distributions. CMStatistics 2018 - 11th International Conference of the ERCIM WG on Computational and Methodological Statistics, Dec 2018, Pisa, Italy. ⟨hal-01941682⟩

Share

Metrics

Record views

97