Reweighting simulated events using machine-learning techniques in the CMS experiment

TL;DR

This paper introduces machine-learning techniques to reweight simulated particle collision events in the CMS experiment, reducing computational costs and enabling more precise physics analyses at the LHC.

Contribution

It presents a novel ML-based reweighting method that efficiently adjusts simulated samples for different parameters without rerunning full detector simulations.

Findings

Effective reweighting for model variations

Application to top quark pair production

Facilitates precision measurements at HL-LHC

Abstract

Data analyses in particle physics rely on an accurate simulation of particle collisions and a detailed simulation of detector effects to extract physics knowledge from the recorded data. Event generators together with a GEANT-based simulation of the detectors are used to produce large samples of simulated events for analysis by the LHC experiments. These simulations come at a high computational cost, where the detector simulation and reconstruction algorithms have the largest CPU demands. This article describes how machine-learning (ML) techniques are used to reweight simulated samples obtained with a given set of model parameters to samples with different parameters or samples obtained from entirely different simulation programs. The ML reweighting method avoids the need for simulating the detector response multiple times by incorporating the relevant information in a single sample through event weights. Results are presented for reweighting to model variations and higher-order calculations in simulated top quark pair production at the LHC. This ML-based reweighting is an important element of the future computing model of the CMS experiment and will facilitate precision measurements at the High-Luminosity LHC.