Quantum Vision Transformers for Quark-Gluon Classification

TL;DR

This paper presents a hybrid quantum-classical vision transformer designed for particle physics data analysis, specifically for classifying quark and gluon jets, demonstrating comparable performance to classical models with similar parameters.

Contribution

It introduces a novel quantum-enhanced vision transformer architecture that integrates variational quantum circuits into attention and MLP components for particle classification.

Findings

Achieved near-classical classification performance on jet data

Successfully trained and evaluated the quantum model via simulations

Addresses computational challenges in high-energy physics data analysis

Abstract

We introduce a hybrid quantum-classical vision transformer architecture, notable for its integration of variational quantum circuits within both the attention mechanism and the multi-layer perceptrons. The research addresses the critical challenge of computational efficiency and resource constraints in analyzing data from the upcoming High Luminosity Large Hadron Collider, presenting the architecture as a potential solution. In particular, we evaluate our method by applying the model to multi-detector jet images from CMS Open Data. The goal is to distinguish quark-initiated from gluon-initiated jets. We successfully train the quantum model and evaluate it via numerical simulations. Using this approach, we achieve classification performance almost on par with the one obtained with the completely classical architecture, considering a similar number of parameters.