Winner-takes-all learners are geometry-aware conditional density estimators - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Winner-takes-all learners are geometry-aware conditional density estimators

Résumé

Winner-takes-all training is a simple learning paradigm, which handles ambiguous tasks by predicting a set of plausible hypotheses. Recently, a connection was established between Winner-takes-all training and centroidal Voronoi tessellations, showing that, once trained, hypotheses should quantize optimally the shape of the conditional distribution to predict. However, the best use of these hypotheses for uncertainty quantification is still an open question. In this work, we show how to leverage the appealing geometric properties of the Winner-takes-all learners for conditional density estimation, without modifying its original training scheme. We theoretically establish the advantages of our novel estimator both in terms of quantization and density estimation, and we demonstrate its competitiveness on synthetic and real-world datasets, including audio data.
Fichier principal
Vignette du fichier
main_paper.pdf (4.17 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04574640 , version 1 (06-06-2024)

Identifiants

  • HAL Id : hal-04574640 , version 1

Citer

Victor Letzelter, David Perera, Cédric Rommel, Mathieu Fontaine, Slim Essid, et al.. Winner-takes-all learners are geometry-aware conditional density estimators. International Conference on Machine Learning, Jul 2024, Vienne (Autriche), Austria. ⟨hal-04574640⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More