Quantum Machine Learning at LHCb

At the LHCb experiment, it is mandatory to identify jets produced by $b$ and $\bar{b}$ quarks (b-jet charge tagging), since it is fundamental in several Physics studies, e.g. the measurement of the $b$-$\bar{b}$ production asymmetry, which could be sensitive to New Physics channels. Being a classification problem, Machine Learning techniques, such as Deep Neural Networks, have been used to solve this problem. In this work, we present a new approach to b-jet charge tagging based on Quantum Machine Learning techniques, trained on LHCb simulated data. Performance comparisons with other classical algorithms are also presented.