Improved Probabilistic Regression Using Diffusion Models
MCML Authors
Philipp Scholl
Gitta Kutyniok
Prof. Dr.
Core PI
Abstract
Philipp Scholl
Gitta Kutyniok
Prof. Dr.
Core PI
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 high-dimensional data, their usage in regression tasks often lacks uncertainty-related evaluation. We propose a novel diffusion-based framework for probabilistic regression where we model the full distribution of the diffusion noise, enabling adaptation to diverse tasks and enhanced uncertainty quantification.
inproceedings KBS+26
NLDL 2026
Northern Lights Deep Learning Conference. Tromsø, Norway, Jan 06-08, 2026. To be published. Preprint available.Authors
C. Kneissl • C. Bülte • P. Scholl • G. KutyniokLinks
URLResearch Area
BibTeXKey: KBS+26