Uncertainty-Aware Diffusion Models for Probabilistic Regression

Kneißl, Carlo; Bülte, Christopher; Scholl, Philipp und Kutyniok, Gitta (2024): Uncertainty-Aware Diffusion Models for Probabilistic Regression. EIML@EurIPS 2025 Workshop: Epistemic Intelligence in Machine Learning, Copenhagen, Denmark, 6. Dezember 2025.

Abstract

Probabilistic regression models the entire predictive distribution of a response variable, offering richer insights than classical point estimates and directly allowing for uncertainty quantification. While diffusion-based generative models have shown remarkable success in generating complex, high-dimensional data, their usage in general regression tasks often lacks uncertainty-related evaluation and remains limited to domain-specific applications. We propose a novel diffusion-based framework for probabilistic regression that learns predictive distributions in a nonparametric way. More specifically, we propose to model the full distribution of the diffusion noise, enabling adaptation to diverse tasks and automatic estimation of epistemic uncertainty. We propose different noise parameterizations, analyze their trade-offs, and evaluate our framework across a broad range of regression tasks. Across several experiments, our approach shows superior performance against existing baselines, while delivering calibrated uncertainty estimates, demonstrating its versatility as a tool for probabilistic prediction.

• Item Type: Conference or Workshop Item (Paper)
• Faculties: Mathematics, Computer Science and Statistics > Mathematics > Bavarian Chair for Mathematical Foundations of Artificial Intelligence
• Subjects: 500 Science > 510 Mathematics
• Language: English