8โ€“12 Sept 2025
Hamburg, Germany
Europe/Berlin timezone

ML-unfolding without prior dependence

10 Sept 2025, 11:10
20m
ESA W 'West Wing'

ESA W 'West Wing'

Poster Track 3: Computations in Theoretical Physics: Techniques and Methods Poster session with coffee break

Speaker

Theo Heimel (UCLouvain)

Description

Machine learning methods enable unbinned and full-dimensional unfolding. However, existing approaches, both classifier-based and generative, suffer from prior dependence. We propose a new method for ML-based unfolding that is completely prior independent and infers the unfolded distribution in a fully frequentist manner. Using several benchmark datasets, we demonstrate that the method can infer unfolded distributions to percent-level precision.

Authors

Anja Butter (Centre National de la Recherche Scientifique (FR)) Michael Kagan (SLAC National Accelerator Laboratory (US)) Nathan Huetsch (Heidelberg University, ITP Heidelberg) Theo Heimel (UCLouvain) Tilman Plehn

Presentation materials