Machine learning-based event generator for electron-proton scattering

Authors:

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.
Funding Information
  • Laboratory Directed Research and Development (LD2122)
  • U.S. Department of Energy (DE-AC05-06OR23177)
  • Deutsche Forschungsgemeinschaft (40824754)
  • National Science Foundation (PHY-2012865)
  • Jefferson Science Associates, LLC

This publication has 20 references indexed in Scilit: