TY - JOUR
T1 - Application of quantum machine learning using the quantum kernel algorithm on high energy physics analysis at the LHC
AU - Wu, Sau Lan
AU - Sun, Shaojun
AU - Guan, Wen
AU - Zhou, Chen
AU - Chan, Jay
AU - Cheng, Chi Lung
AU - Pham, Tuan
AU - Qian, Yan
AU - Wang, Alex Zeng
AU - Zhang, Rui
AU - Livny, Miron
AU - Glick, Jennifer
AU - Barkoutsos, Panagiotis Kl
AU - Woerner, Stefan
AU - Tavernelli, Ivano
AU - Carminati, Federico
AU - Di Meglio, Alberto
AU - Li, Andy C.Y.
AU - Lykken, Joseph
AU - Spentzouris, Panagiotis
AU - Chen, Samuel Yen Chi
AU - Yoo, Shinjae
AU - Wei, Tzu Chieh
N1 - Publisher Copyright:
© 2021 authors.
PY - 2021/9
Y1 - 2021/9
N2 - Quantum machine learning could possibly become a valuable alternative to classical machine learning for applications in high energy physics by offering computational speedups. In this study, we employ a support vector machine with a quantum kernel estimator (QSVM-Kernel method) to a recent LHC flagship physics analysis: tt¯H (Higgs boson production in association with a top quark pair). In our quantum simulation study using up to 20 qubits and up to 50000 events, the QSVM-Kernel method performs as well as its classical counterparts in three different platforms from Google Tensorflow Quantum, IBM Quantum, and Amazon Braket. Additionally, using 15 qubits and 100 events, the application of the QSVM-Kernel method on the IBM superconducting quantum hardware approaches the performance of a noiseless quantum simulator. Our study confirms that the QSVM-Kernel method can use the large dimensionality of the quantum Hilbert space to replace the classical feature space in realistic physics data sets.
AB - Quantum machine learning could possibly become a valuable alternative to classical machine learning for applications in high energy physics by offering computational speedups. In this study, we employ a support vector machine with a quantum kernel estimator (QSVM-Kernel method) to a recent LHC flagship physics analysis: tt¯H (Higgs boson production in association with a top quark pair). In our quantum simulation study using up to 20 qubits and up to 50000 events, the QSVM-Kernel method performs as well as its classical counterparts in three different platforms from Google Tensorflow Quantum, IBM Quantum, and Amazon Braket. Additionally, using 15 qubits and 100 events, the application of the QSVM-Kernel method on the IBM superconducting quantum hardware approaches the performance of a noiseless quantum simulator. Our study confirms that the QSVM-Kernel method can use the large dimensionality of the quantum Hilbert space to replace the classical feature space in realistic physics data sets.
UR - https://www.scopus.com/pages/publications/85115887728
U2 - 10.1103/PhysRevResearch.3.033221
DO - 10.1103/PhysRevResearch.3.033221
M3 - Article
AN - SCOPUS:85115887728
SN - 2643-1564
VL - 3
JO - Physical Review Research
JF - Physical Review Research
IS - 3
M1 - 033221
ER -