Resolving Combinatorial Ambiguities in Dilepton $t \bar t$ Event Topologies with Neural Networks

TL;DR

This paper demonstrates that deep learning methods significantly improve the accuracy of pairing leptons with b quarks in dileptonic top quark events at the LHC, especially when mass spectrum information is unavailable.

Contribution

The study introduces deep learning approaches, including attention-based networks and Lorentz Boost Networks, to resolve combinatorial ambiguities in dileptonic top quark events, outperforming traditional kinematic variable methods.

Findings

Deep learning improves pairing accuracy in dileptonic $t\bar t$ events.

Attention-based and Lorentz Boost Networks outperform existing methods.

Performance gains are significant even without mass spectrum information.

Abstract

We study the potential of deep learning to resolve the combinatorial problem in SUSY-like events with two invisible particles at the LHC. As a concrete example, we focus on dileptonic $t \bar t$ events, where the combinatorial problem becomes an issue of binary classification: pairing the correct lepton with each $b$ quark coming from the decays of the tops. We investigate the performance of a number of machine learning algorithms, including attention-based networks, which have been used for a similar problem in the fully-hadronic channel of $t\bar t$ production; and the Lorentz Boost Network, which is motivated by physics principles. We then consider the general case when the underlying mass spectrum is unknown, and hence no kinematic endpoint information is available. Compared against existing methods based on kinematic variables, we demonstrate that the efficiency for selecting the correct pairing is greatly improved by utilizing deep learning techniques.