TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.17.2.045
TI  - Towards a data-driven model of hadronization using normalizing flows
PY  - 2024/08/12
UR  - https://www.scipost.org/SciPostPhys.17.2.045
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 17
IS  - 2
SP  - 045
A1  - Bierlich, Christian
AU  - Ilten, Philip
AU  - Menzo, Tony
AU  - Mrenna, Stephen
AU  - Szewc, Manuel
AU  - Wilkinson, Michael K.
AU  - Youssef, Ahmed
AU  - Zupan, Jure
AB  - We introduce a model of hadronization based on invertible neural networks that faithfully reproduces a simplified version of the Lund string model for meson hadronization. Additionally, we introduce a new training method for normalizing flows, termed MAGIC, that improves the agreement between simulated and experimental distributions of high-level (macroscopic) observables by adjusting single-emission (microscopic) dynamics. Our results constitute an important step toward realizing a machine-learning based model of hadronization that utilizes experimental data during training. Finally, we demonstrate how a Bayesian extension to this normalizing-flow architecture can be used to provide analysis of statistical and modeling uncertainties on the generated observable distributions.
ER  -

@Article{10.21468/SciPostPhys.17.2.045,
	title={{Towards a data-driven model of hadronization using normalizing flows}},
	author={Christian Bierlich and Phil Ilten and Tony Menzo and Stephen Mrenna and Manuel Szewc and Michael K. Wilkinson and Ahmed Youssef and Jure Zupan},
	journal={SciPost Phys.},
	volume={17},
	pages={045},
	year={2024},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.17.2.045},
	url={https://scipost.org/10.21468/SciPostPhys.17.2.045},
}