Enregistré dans:
Détails bibliographiques
Auteurs principaux: Azizi, Ilia, Boldi, Marc-Olivier, Chavez-Demoulin, Valérie
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.18176
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908562293260288
author Azizi, Ilia
Boldi, Marc-Olivier
Chavez-Demoulin, Valérie
author_facet Azizi, Ilia
Boldi, Marc-Olivier
Chavez-Demoulin, Valérie
contents This work introduces the Supervised Expectation-Maximization Framework (SEMF), a versatile and model-agnostic approach for generating prediction intervals with any ML model. SEMF extends the Expectation-Maximization algorithm, traditionally used in unsupervised learning, to a supervised context, leveraging latent variable modeling for uncertainty estimation. Through extensive empirical evaluation of diverse simulated distributions and 11 real-world tabular datasets, SEMF consistently produces narrower prediction intervals while maintaining the desired coverage probability, outperforming traditional quantile regression methods. Furthermore, without using the quantile (pinball) loss, SEMF allows point predictors, including gradient-boosted trees and neural networks, to be calibrated with conformal quantile regression. The results indicate that SEMF enhances uncertainty quantification under diverse data distributions and is particularly effective for models that otherwise struggle with inherent uncertainty representation.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18176
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SEMF: Supervised Expectation-Maximization Framework for Predicting Intervals
Azizi, Ilia
Boldi, Marc-Olivier
Chavez-Demoulin, Valérie
Machine Learning
This work introduces the Supervised Expectation-Maximization Framework (SEMF), a versatile and model-agnostic approach for generating prediction intervals with any ML model. SEMF extends the Expectation-Maximization algorithm, traditionally used in unsupervised learning, to a supervised context, leveraging latent variable modeling for uncertainty estimation. Through extensive empirical evaluation of diverse simulated distributions and 11 real-world tabular datasets, SEMF consistently produces narrower prediction intervals while maintaining the desired coverage probability, outperforming traditional quantile regression methods. Furthermore, without using the quantile (pinball) loss, SEMF allows point predictors, including gradient-boosted trees and neural networks, to be calibrated with conformal quantile regression. The results indicate that SEMF enhances uncertainty quantification under diverse data distributions and is particularly effective for models that otherwise struggle with inherent uncertainty representation.
title SEMF: Supervised Expectation-Maximization Framework for Predicting Intervals
topic Machine Learning
url https://arxiv.org/abs/2405.18176