HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model

TMLR Paper5197 Authors

Abstract: Uncertainty quantification is critical for ensuring robustness in high-stakes machine learning applications. We introduce HybridFlow, a novel hybrid architecture that integrates normalizing flows for modeling aleatoric uncertainty with a probabilistic predictor model with the ability to quantify epistemic uncertainty, providing precise uncertainty estimates that are easily integrated into existing model architectures without sacrificing predictive performance. HybridFlow improves upon previous uncertainty quantification frameworks across a range of regression tasks, such as depth estimation, a collection of regression benchmarks, and a scientific case study of ice sheet emulation. We also provide an analysis of the quantified uncertainty, showing that the uncertainty quantified by HybridFlow is calibrated and better aligns with model error than existing methods for quantifying aleatoric and epistemic uncertainty. HybridFlow addresses a key challenge in Bayesian deep learning, unifying aleatoric and epistemic uncertainty modeling in a single robust framework.

Submission Length: Long submission (more than 12 pages of main content)

Assigned Action Editor: ~Manuel_Haussmann1

Submission Number: 5197