Application of Quantum Machine Learning in a Higgs Physics Study at the CEPC

Aug 3, 2026

Upload by Violet

Machine learning has become indispensable in particle physics, enabling particle reconstruction and event classification, yet conventional approaches still face limitations that quantum computing may overcome. This study introduces a QSVM-Kernel quantum support-vector approach to analyze the e+ e− → ZH process at the Circular Electron-Positron Collider (CEPC), a proposed Higgs factory for electroweak symmetry breaking studies. Using 6-qubit simulators, the method is optimized and reaches classification performance comparable to classical SVM. Results validated on 6-qubit IBM and Origin Quantum hardware show behavior approaching noiseless simulators, with Origin Quantum consistent with IBM within uncertainties.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Introduction

Higgs boson and Higgs factory motivation

Machine learning in particle physics

Quantum machine learning and QSVM-Kernel

Quantum computing developments and prior proof-of-principle studies

arXiv :2209 . 12788v2 [hep-ex] 12 Mar 2024 Application of Quantum Machine Learning in a Higgs Physics Study at the CEPC Abdualazem Fadol 1 ,5 , Qiyu Sha 1 ,2 , Yaquan Fang 1 ,2 , Zhan Li 1 ,2 , Sitian Qian 3 , Yuyang Xiao 3 , Yu Zhang 4 , Chen Zhou 3 , * 1 Institute of High Energy Physics, 19B Yuquan Road, Shijingshan District, Beijing 100049, China 2 University of Chinese Academy of Sciences, 19A Yuquan Road, Shijingshan District, Beijing 100049, China 3 State Key Laboratory of Nuclear Physics and Technology, School of Physics, Peking University, 209 Chengfu Road, Haidian District, Beijing 100871, China 4 Qujing Normal University, 222 Sanjiang Road, Qilin District, Qujing 655011, Yunnan Province, China 5 Spallation Neutron Source Science centre, Dongguan 523803, China E-mail:∗[czhouphy@pku.edu.cn](czhouphy@pku.edu.cn) Abstract. Machine learning has blossomed in recent decades and has become essential in many fields. It significantly solved some problems in particle physics—particle reconstruction, event classification, etc. However, it is now time to break the limitation of conventional machine learning with quantum computing. A supportvector machine algorithm with a quantum kernel estimator (QSVM-Kernel) leverages high-dimensional quantum state space to identify a signal from backgrounds. In this study, we have pioneered employing this quantum machine learning algorithm to study the e+ e − → ZH process at the Circular Electron-Positron Collider (CEPC), a proposed Higgs factory to study electroweak symmetry breaking of particle physics. Using 6 qubits on quantum computer simulators, we optimised the QSVMKernel algorithm and obtained a classification performance similar to the classical support-vector machine algorithm. Furthermore, we have validated the QSVM-Kernel algorithm using 6-qubits on quantum computer hardware from both IBM and Origin Quantum: the classification performances of both are approaching noiseless quantum computer simulators. In addition, the Origin Quantum hardware results are similar to the IBM Quantum hardware within the uncertainties in our study. Our study shows that state-of-the-art quantum computing technologies could be utilised by particle physics, a branch of fundamental science that relies on big experimental data. Keywords: Quantum computing, Machine Learning, Particle Physics, Higgs Factory 1. Introduction The discovery of the Higgs boson [1, 2] by the ATLAS and CMS experiments at the Large Hadron Collider (LHC) in 2012 was a significant milestone in particle physics. 2 It confirmed the fundamental particle spectrum of the Standard Model and opened a new window to refine our understanding of particle physics. The Higgs boson is needed to break the electroweak symmetry in the Standard Model. Since then, the LHC experiments have performed extensive studies on the Higgs boson properties: clues for new physics would emerge if any measurement disagrees with the Standard Model prediction. However, there is no significant hint of new physics has been found to date. Higgs factories [3, 4, 5, 6] based on lepton colliders have been proposed to perform more precise measurements of the Higgs boson properties and study electroweak symmetry breaking of particle physics. The Circular Electron-Positron Collider (CEPC), presented by Chinese scientists, is one such collider that acts as a Higgs factory. It will be located in a tunnel with a circumference of approximately 100 km colliding electron-positron pairs at a centre-of-mass energy of up to 240 GeV, upgradable to 360 GeV. Machine learning has enjoyed widespread success in detector simulation, particle reconstruction and data analyses of experimental particle physics and dramatically enhances the ability to achieve physics discovery. For instance, machine learning algorithms are used in ATLAS and CMS experiments to help separate signals from backgrounds in the observation of the Higgs boson production in association with atop q

FAQs

What quantum machine learning method is used in the study?

The study uses a support-vector machine algorithm with a quantum kernel estimator (QSVM-Kernel) to leverage high-dimensional quantum state spaces for classification.

What physics process and collider are investigated?

The method is applied to the e+ e− → ZH process at the Circular Electron-Positron Collider (CEPC), a proposed Higgs factory for electroweak symmetry breaking research.

How is the QSVM-Kernel algorithm validated?

Validation is performed using 6-qubit quantum computer simulators and further tested on 6-qubit hardware from both IBM and Origin Quantum, comparing classification performance against noiseless simulator behavior.

Aug 3, 2026

Upload by Violet