Sparse and geometry-aware generalisation of the mutual information for joint discriminative clustering and feature selection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ohl, Louis, Mattei, Pierre-Alexandre, Bouveyron, Charles, Leclercq, Mickaël, Droit, Arnaud, Precioso, Frédéric
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909260849348608
author Ohl, Louis
Mattei, Pierre-Alexandre
Bouveyron, Charles
Leclercq, Mickaël
Droit, Arnaud
Precioso, Frédéric
author_facet Ohl, Louis
Mattei, Pierre-Alexandre
Bouveyron, Charles
Leclercq, Mickaël
Droit, Arnaud
Precioso, Frédéric
contents Feature selection in clustering is a hard task which involves simultaneously the discovery of relevant clusters as well as relevant variables with respect to these clusters. While feature selection algorithms are often model-based through optimised model selection or strong assumptions on the data distribution, we introduce a discriminative clustering model trying to maximise a geometry-aware generalisation of the mutual information called GEMINI with a simple l1 penalty: the Sparse GEMINI. This algorithm avoids the burden of combinatorial feature subset exploration and is easily scalable to high-dimensional data and large amounts of samples while only designing a discriminative clustering model. We demonstrate the performances of Sparse GEMINI on synthetic datasets and large-scale datasets. Our results show that Sparse GEMINI is a competitive algorithm and has the ability to select relevant subsets of variables with respect to the clustering without using relevance criteria or prior hypotheses.
format Preprint
id arxiv_https___arxiv_org_abs_2302_03391
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Sparse and geometry-aware generalisation of the mutual information for joint discriminative clustering and feature selection
Ohl, Louis
Mattei, Pierre-Alexandre
Bouveyron, Charles
Leclercq, Mickaël
Droit, Arnaud
Precioso, Frédéric
Machine Learning
Artificial Intelligence
Computation
Methodology
62H30
G.3
Feature selection in clustering is a hard task which involves simultaneously the discovery of relevant clusters as well as relevant variables with respect to these clusters. While feature selection algorithms are often model-based through optimised model selection or strong assumptions on the data distribution, we introduce a discriminative clustering model trying to maximise a geometry-aware generalisation of the mutual information called GEMINI with a simple l1 penalty: the Sparse GEMINI. This algorithm avoids the burden of combinatorial feature subset exploration and is easily scalable to high-dimensional data and large amounts of samples while only designing a discriminative clustering model. We demonstrate the performances of Sparse GEMINI on synthetic datasets and large-scale datasets. Our results show that Sparse GEMINI is a competitive algorithm and has the ability to select relevant subsets of variables with respect to the clustering without using relevance criteria or prior hypotheses.
title Sparse and geometry-aware generalisation of the mutual information for joint discriminative clustering and feature selection
topic Machine Learning
Artificial Intelligence
Computation
Methodology
62H30
G.3
url https://arxiv.org/abs/2302.03391