Towards a data-driven model of hadronization using normalizing flows

Summary, in English

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.

• Author: Christian Bierlich; Phil Ilten; Tony Menzo; Stephen Mrenna; Manuel Szewc; Michael K. Wilkinson; Ahmed Youssef; Jure Zupan
• Department/s: Particle and nuclear physics
• Publishing year: 2024-08
• Language: English
• Publication/Series: SciPost Physics
• Volume: 17
• Issue: 2
• Links: http://dx.doi.org/10.21468/SciPostPhys.17.2.045
• Document type: Journal article
• Publisher: SciPost
• Topic: Subatomic Physics
• Status: Published
• ISBN/ISSN/Other: ISSN: 2542-4653