Abstract
We have developed two quantum classifier models for the ttH classification problem, both of which fall into the category of hybrid quantumclassical algorithms for Noisy Intermediate Scale Quantum devices (NISQ). Our results, along with other studies, serve as a proof of concept that Quantum Machine Learning (QML) methods can have similar or better performance, in specific cases of low number of training samples, with respect to conventional ML methods even with a limited number of qubits available in current hardware. To utilise algorithms with a low number of qubits — to accommodate for limitations in both simulation hardware and real quantum hardware — we investigated different feature reduction methods. Their impact on the performance of both the classical and quantum models was assessed. We addressed different implementations of two QML models, representative of the two main approaches to supervised quantum machine learning today: a Quantum Support Vector Machine (QSVM), a kernel-based method, and a Variational Quantum Circuit (VQC), a variational approach.
Highlights
Identifying the Higgs boson production in association with top quark - antiquark pairs in which the Higgs decays into a pair of bottom quark-antiquark allows studying the Yukawa coupling of the Higgs boson in a purely fermionic process
We developed two quantum classifier models for the ttH(bb) classification problem, both of which fall into the category of hybrid quantum-classical algorithms for Noisy Intermediate Scale Quantum devices (NISQ): a Quantum Support Vector Machine (QSVM), a kernelbased method, and a Variational Quantum Circuit (VQC), a variational approach
The DNN and Boosted Decision Trees (BDTs) models serve as a benchmark of standard classical methods used in HEP, to which we can compare the performance of the quantum models
Summary
Identifying the Higgs boson production in association with top quark - antiquark pairs in which the Higgs decays into a pair of bottom quark-antiquark allows studying the Yukawa coupling of the Higgs boson in a purely fermionic process. The complex final state of the ttH(bb) process comes with a large number of jets, but allows studying the purely fermionic Higgs production and decay. Apart from the training using all the input features (67) the models were trained using only the reduced set of features (16) of the latent space of one of the developed Autoencoders (see Sec. 2.2) The goal is to design the quantum circuit in such a way that, firstly, it transforms the input data in a manner that is exponentially hard to simulate classically; and, secondly, the quantum feature map allows the background and signal events to be more distinguishable in the feature space than in the input one.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
