Unweighting multijet event generation using factorisation-aware neural networks

Janßen, Timo; Maître, Daniel; Schumann, Steffen; Siegert, Frank; Truong, Henry

Abstract

In this article we combine a recently proposed method for factorisation-aware matrix element surrogates with an unbiased unweighting algorithm. We show that employing a sophisticated neural network emulation of QCD multijet matrix elements based on dipole factorisation can lead to a drastic acceleration of unweighted event generation. We train neural networks for a selection of partonic channels contributing at the tree-level to Z+4,5 jets and t¯t + 3, 4 jets production at the LHC which necessitates a generalisation of the dipole emulation model to include initial state partons as well as massive final state quarks. We also present first steps towards the emulation of colour-sampled amplitudes. We incorporate these emulations as fast and accurate surrogates in a two-stage rejection sampling algorithm within the SHERPA Monte Carlo that yields unbiased unweighted events suitable for phenomenological analyses and post-processing in experimental workflows, e.g. as input to a time-consuming detector simulation. For the computational cost of unweighted events we achieve a reduction by factors between 16 and
350 for the considered channels.

Citation

Janßen, T., Maître, D., Schumann, S., Siegert, F., & Truong, H. (2023). Unweighting multijet event generation using factorisation-aware neural networks. SciPost Physics, 15(3), Article 107. https://doi.org/10.21468/scipostphys.15.3.107

• Journal Article Type: Article
• Acceptance Date: Jul 20, 2023
• Online Publication Date: Sep 21, 2023
• Publication Date: Sep 21, 2023
• Deposit Date: Mar 15, 2024
• Publicly Available Date: Mar 15, 2024
• Journal: SciPost Physics
• Print ISSN: 2542-4653
• Publisher: SciPost
• Peer Reviewed: Peer Reviewed
• Volume: 15
• Issue: 3
• Article Number: 107
• DOI: https://doi.org/10.21468/scipostphys.15.3.107
• Keywords: General Physics and Astronomy
• Public URL: https://durham-repository.worktribe.com/output/2269875