Machine learning techniques in searches for tt̄h in the h → bb̄ decay channel

Abstract

Study of the production of pairs of top quarks in association with a Higgs boson is one of the primary goals of the Large Hadron Collider over the next decade, as measurements of this process may help us to understand whether the uniquely large mass of the top quark plays a special role in electroweak symmetry breaking. Higgs bosons decay predominantly to bb̄, yielding signatures for the signal that are similar to tt̄ + jets with heavy flavor. Though particularly challenging to study due to the similar kinematics between signal and background events, such final states (tt̄ bb̄) are an important channel for studying the top quark Yukawa coupling. This paper presents a systematic study of machine learning (ML) methods for detecting tt̄h in the h → bb̄ decay channel. Among the eight ML methods tested, we show that two models, extreme gradient boosted trees and neural network models, outperform alternative methods. We further study the effectiveness of ML algorithms by investigating the impact of feature set and data size, as well as the structure of the models. While extended feature set and larger training sets expectedly lead to improvement of performance, shallow models deliver comparable or better performance than their deeper counterparts. Our study suggests that ensembles of trees and neurons, not necessarily deep, work effectively for the problem of tt̄h detection.