TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.18.6.200
TI  - Generative unfolding with distribution mapping
PY  - 2025/06/20
UR  - https://scipost.org/SciPostPhys.18.6.200
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 18
IS  - 6
SP  - 200
A1  - Butter, Anja
AU  - Diefenbacher, Sascha
AU  - Huetsch, Nathan
AU  - Mikuni, Vinicius
AU  - Nachman, Benjamin
AU  - Palacios Schweitzer, Sofia
AU  - Plehn, Tilman
AB  - Machine learning enables unbinned, highly-differential cross section measurements. A recent idea uses generative models to morph a starting simulation into the unfolded data. We show how to extend two morphing techniques, Schrödinger Bridges and Direct Diffusion, in order to ensure that the models learn the correct conditional probabilities. This brings distribution mapping (DM) to a similar level of accuracy as the state-of-the-art conditional generative unfolding methods. Numerical results are presented with a standard benchmark dataset of single jet substructure as well as for a new dataset describing a 22-dimensional phase space of $Z+2$-jets.
ER  -

@Article{10.21468/SciPostPhys.18.6.200,
	title={{Generative unfolding with distribution mapping}},
	author={Anja Butter and Sascha Diefenbacher and Nathan Huetsch and Vinicius Mikuni and Benjamin Nachman and Sofia Palacios Schweitzer and Tilman Plehn},
	journal={SciPost Phys.},
	volume={18},
	pages={200},
	year={2025},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.18.6.200},
	url={https://scipost.org/10.21468/SciPostPhys.18.6.200},
}