Saved in:
Bibliographic Details
Main Authors: Marco, Adriel Sosa, Kirwan, John Daniel, Toumpa, Alexia, Gerasimou, Simos
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.00835
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912738371960832
author Marco, Adriel Sosa
Kirwan, John Daniel
Toumpa, Alexia
Gerasimou, Simos
author_facet Marco, Adriel Sosa
Kirwan, John Daniel
Toumpa, Alexia
Gerasimou, Simos
contents Quantifying uncertainty in deep regression models is important both for understanding the confidence of the model and for safe decision-making in high-risk domains. Existing approaches that yield prediction intervals overlook distributional information, neglecting the effect of multimodal or asymmetric distributions on decision-making. Similarly, full or approximated Bayesian methods, while yielding the predictive posterior density, demand major modifications to the model architecture and retraining. We introduce MCNF, a novel post hoc uncertainty quantification method that produces both prediction intervals and the full conditioned predictive distribution. MCNF operates on top of the underlying trained predictive model; thus, no predictive model retraining is needed. We provide experimental evidence that the MCNF-based uncertainty estimate is well calibrated, is competitive with state-of-the-art uncertainty quantification methods, and provides richer information for downstream decision-making tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00835
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
Marco, Adriel Sosa
Kirwan, John Daniel
Toumpa, Alexia
Gerasimou, Simos
Machine Learning
Quantifying uncertainty in deep regression models is important both for understanding the confidence of the model and for safe decision-making in high-risk domains. Existing approaches that yield prediction intervals overlook distributional information, neglecting the effect of multimodal or asymmetric distributions on decision-making. Similarly, full or approximated Bayesian methods, while yielding the predictive posterior density, demand major modifications to the model architecture and retraining. We introduce MCNF, a novel post hoc uncertainty quantification method that produces both prediction intervals and the full conditioned predictive distribution. MCNF operates on top of the underlying trained predictive model; thus, no predictive model retraining is needed. We provide experimental evidence that the MCNF-based uncertainty estimate is well calibrated, is competitive with state-of-the-art uncertainty quantification methods, and provides richer information for downstream decision-making tasks.
title Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
topic Machine Learning
url https://arxiv.org/abs/2512.00835