From Qubits to Couplings: A Hybrid Quantum Machine Learning Framework for LHC Physics

TL;DR

This paper introduces a hybrid quantum-classical machine learning framework that enhances the sensitivity of double Higgs boson searches at the LHC, outperforming existing models and providing tighter constraints on Higgs couplings.

Contribution

The paper presents a novel hybrid quantum machine learning model combining quantum circuits with classical neural networks for particle physics analysis.

Findings

Hybrid model doubles the sensitivity over classical models.

Achieves expected 95% CL upper limit of 1.9 times the SM cross-section.

Improves constraints on Higgs self-coupling and quartic couplings.

Abstract

In this paper, we propose a new Hybrid Quantum Machine Learning (HyQML) framework to improve the sensitivity of double Higgs boson searches in the $HH \to b\bar{b}\gamma\gamma$ final state at $\sqrt{s}$ = 13.6 TeV. The proposed model combines parameterized quantum circuits with a classical neural network meta-model, enabling event-level features to be embedded in a quantum feature space while maintaining the optimization stability of classical learning. The hybrid model outperforms both a state-of-the-art XGBoost model and a purely quantum implementation by a factor of two, achieving an expected 95% CL upper limit on the non-resonant double Higgs boson production cross-section of $1.9\times\sigma_{\text{SM}}$ and $2.1\times\sigma_{\text{SM}}$ under background normalization uncertainties of 10% and 50%, respectively. In addition, expected constraints on the Higgs boson self-coupling $\kappa_{\lambda}$ and quartic vector-boson-Higgs coupling $\kappa_{2V}$ are found to be improved compared to the classical and purely quantum models.