Machine learning approaches for parameter reweighting in MC samples of top quark production in CMS

In particle physics, Monte Carlo (MC) event generators are needed to compare theory to the measured data. Many MC samples have to be generated to account for theoretical systematic uncertainties, at a significant computational cost. Therefore, the MC statistic becomes a limiting factor for most measurements and the significant computational cost of these programs a bottleneck in most physics analyses. In this note, the Deep neural network using Classification for Tuning and Reweighting (DCTR) method is evaluated on MC sample of top pair production in CMS. DCTR is a method, based on a Deep Neural Network (DNN) technique, to reweight simulations to different model parameters by using the full kinematic information in the event. This methodology avoids the need for simulating the detector response multiple times by incorporating the relevant variations in a single sample. In this note, DCTR method is evaluated in two different scenarios: the discrete reweighting of the hdamp variation in Parton-level Powheg HVQ events and the continuous reweighting of a b-fragmentation function parameter in particle-level Pythia8 events. The results are presented in this note.