Boosting Sensitivity to $HH\to b\bar{b} \gamma\gamma$ with Graph Neural Networks and XGBoost

TL;DR

This paper demonstrates that using graph neural networks and XGBoost can significantly improve the sensitivity of double Higgs boson searches in the $b\bar{b}\gamma\gamma$ channel at 13.6 TeV, surpassing traditional methods.

Contribution

The study introduces a geometrical graph neural network classifier that outperforms XGBoost in Higgs pair search sensitivity at the LHC.

Findings

Graph neural network outperforms XGBoost by 28% in expected limit improvement.

Significant enhancement in Higgs self-coupling constraints compared to ATLAS results.

Machine learning models improve the detection sensitivity for double Higgs production.

Abstract

In this paper, we explore the use of advanced machine learning (ML) techniques to enhance the sensitivity of double Higgs boson searches in the \( HH \to b\bar{b}\gamma\gamma \) decay channel at $\sqrt{s} = $ 13.6 TeV. Two ML models are implemented and compared: a tree-based classifier using XGBoost, and a geometrical-based graph neural network classifier (GNN). We show that the geometrical model outperform the traditional XGBoost classifier improving the expected 95\% CL upper limit on the double Higgs boson production cross-section by 28\%. Our results are compared to the latest ATLAS experiment results, showing significant improvement of both upper limit and Higgs boson self-coupling ($\kappa_{\lambda}$) constraints.