Document Type

Article

Publication Date

2022

DOI

10.1103/PhysRevD.106.096002

Publication Title

Physical Review D

Volume

106

Issue

9

Pages

096002 (1-9)

Abstract

We present a new machine learning-based Monte Carlo event generator using generative adversarial networks (GANs) that can be trained with calibrated detector simulations to construct a vertex-level event generator free of theoretical assumptions about femtometer scale physics. Our framework includes a GAN-based detector folding as a fast-surrogate model that mimics detector simulators. The framework is tested and validated on simulated inclusive deep-inelastic scattering data along with existing parametrizations for detector simulation, with uncertainty quantification based on a statistical bootstrapping technique. Our results provide for the first time a realistic proof of concept to mitigate theory bias in inferring vertex-level event distributions needed to reconstruct physical observables.

Rights

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI. Funded by SCOAP3.

Original Publication Citation

Alanazi, Y., Ambrozewicz, P., Battaglieri, M., Hiller Blin, A. N., Kuchera, M. P., Li, Y., Liu, T., McClellan, R. E., Melnitchouk, W., Pritchard, E., Robertson, M., Sato, N., Strauss, R., & Velasco, L. (2022). Machine learning-based event generator for electron-proton scattering. Physical Review D, 106(9), 1-9, Article 096002. https://doi.org/10.1103/PhysRevD.106.096002

ORCID

0000-0002-4677-5018 (Alanazi)

Share

COinS