Uncertainty separation via ensemble quantile regression

2024/12/18 by Navid Ansari, Ansari, Navid, Hans‐Peter Seidel +3
Engineering · #Artificial Intelligence (cs.AI) #Computational Engineering #FOS: Computer and information sciences #Fault Detection and Control Systems #Finance #Machine Learning (cs.LG) #and Science (cs.CE)

paper · pdf · doi:10.48550/arxiv.2412.13738

openalex publication_date 2024/12/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper introduces a novel and scalable framework for uncertainty estimation and separation with applications in data driven modeling in science and engineering tasks where reliable uncertainty quantification is critical. Leveraging an ensemble of quantile regression (E-QR) models, our approach enhances aleatoric uncertainty estimation while preserving the quality of epistemic uncertainty, surpassing competing methods, such as Deep Ensembles (DE) and Monte Carlo (MC) dropout. To address challenges in separating uncertainty types, we propose an algorithm that iteratively improves separation through progressive sampling in regions of high uncertainty. Our framework is scalable to large datasets and demonstrates superior performance on synthetic benchmarks, offering a robust tool for uncertainty quantification in data-driven applications.

Related

• Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification
• Uncertainty Quantification for Regression using Proper Scoring Rules
• Introduction and Exemplars of Uncertainty Decomposition
• Accurate Uncertainty Estimation and Decomposition in Ensemble Learning
• Estimating Uncertainty with Implicit Quantile Network