Abstract
Machine learning technology has the potential to dramatically optimise event generation and simulations. We continue to investigate the use of neural networks to approximate matrix elements for high-multiplicity scattering processes. We focus on the case of loop-induced diphoton production through gluon fusion, and develop a realistic simulation method that can be applied to hadron collider observables. Neural networks are trained using the one-loop amplitudes implemented in the NJet C++ library, and interfaced to the Sherpa Monte Carlo event generator, where we perform a detailed study for 2 → 3 and 2 → 4 scattering problems. We also consider how the trained networks perform when varying the kinematic cuts effecting the phase space and the reliability of the neural network simulations.
Highlights
Algorithms is relatively high, resulting in huge commitments of CPU and personnel resources to obtain the necessary theoretical predictions for current experiments
We focus on the case of loop-induced diphoton production through gluon fusion, and develop a realistic simulation method that can be applied to hadron collider observables
The fact that neural networks (NNs) offer a general function parameterisation that are useful in regression problems is not new in particle physics either: for example, parton distribution functions (PDFs) produced by the NNPDF collaboration [21] have been used for many years by the LHC experiments
Summary
Algorithms is relatively high, resulting in huge commitments of CPU and personnel resources to obtain the necessary theoretical predictions for current experiments. The interface of general one-loop amplitude codes into multi-purpose Monte Carlo (MC) event generators has resulted in a wide variety of simulation options which can offer the best possible theoretical accuracy. Methods that go beyond fixed-order perturbation theory — such as parton shower matching, merging, and jet multiplicities — improve accuracy across important regions of phase space. These simulations add additional strain on the underlying amplitudes. The fact that neural networks (NNs) offer a general function parameterisation that are useful in regression problems is not new in particle physics either: for example, parton distribution functions (PDFs) produced by the NNPDF collaboration [21] have been used for many years by the LHC experiments
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
