Top-philic Machine Learning

Abstract

In this article, we review the application of modern machine-learning (ML) techniques to boost the search for processes involving the top quarks at the LHC. We revisit the formalism of Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), and Attention Mechanisms. Based on recent studies, we explore their applications in designing improved top taggers, top reconstruction, and event classification tasks. We also examine the ML-based likelihood-free inference approach and generative unfolding models, focusing on their applications to scenarios involving top quarks.

A short review prepared by invitation for EPJ Special Topics issue. Version accepted for publication; 45 pages, 17 figures, 1 table; v2: typos corrected

References in corpus (13)

• A Monte Carlo global analysis of the Standard Model Effective Field Theory: the top quark sector
• A generic anti-QCD jet tagger
• Threshold Resummation for the Top Quark Charge Asymmetry
• Weak interaction corrections to hadronic top quark pair production
• Massive color-octet bosons and the charge asymmetries of top quarks at hadron colliders
• Top production at the Tevatron/LHC and nonstandard, strongly interacting spin one particles
• Single-top-quark production in the $t$-channel at NNLO
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• A New Method for Resolving Combinatorial Ambiguities at Hadron Colliders
• Complete SMEFT predictions for four top quark production at hadron colliders
• Boosting to identify: pseudoscalar searches with di-leptonic tops
• Jet-Parton Assignment in ttH Events using Deep Learning
• Resolving Combinatorial Ambiguities in Dilepton $t\bar{t}$ Event Topologies with Constrained $M_2$ Variables