Learning to increase matching efficiency in identifying additional b-jets in the tbartbbarb process

The tbartH(bbarb) process is an essential channel to reveal the Higgs properties but has an irreducible background from the tbartbbarb process, which produces a top quark pair in association with a b quark pair. Therefore, understanding the tbartbbarb process is crucial for improving the sensitivity of a search for the tbartH(bbarb) process. To this end, when measuring the differential cross-section of the tbartbbarb process, we need to distinguish the b-jets originated from top quark decays, and additional b-jets originated from gluon splitting. Since there are no simple identification rules, we adopt deep learning methods to learn from data to identify the additional b-jets from the tbartbbarb events. Specifically, by exploiting the special structure of the tbartbbarb event data, we propose several loss functions that can be minimized to directly increase the matching efficiency, the accuracy of identifying additional b-jets. We discuss the difference between our method and another deep learning-based approach based on binary classification arXiv:1910.14535 using synthetic data. We then verify that additional b-jets can be identified more accurately by increasing matching efficiency directly rather than the binary classification accuracy, using simulated tbartbbarb event data in the lepton+jets channel from pp collision at √s = 13 TeV.