Fitting a Collider in a Quantum Computer: Tackling the Challenges of Quantum Machine Learning for Big Datasets

TL;DR

This paper explores the use of feature selection and data reduction techniques to enable quantum machine learning models to handle large, high-dimensional datasets in high energy physics, comparing their performance to classical methods.

Contribution

It demonstrates that quantum machine learning models can perform comparably to classical models on large datasets using feature selection and data transformation techniques.

Findings

Quantum models are comparable to classical models on large datasets.

Sequential Backward Selection can improve quantum model performance but is less stable.

Principal Component Analysis enhances quantum model stability and performance.

Abstract

Current quantum systems have significant limitations affecting the processing of large datasets with high dimensionality, typical of high energy physics. In the present paper, feature and data prototype selection techniques were studied to tackle this challenge. A grid search was performed and quantum machine learning models were trained and benchmarked against classical shallow machine learning methods, trained both in the reduced and the complete datasets. The performance of the quantum algorithms was found to be comparable to the classical ones, even when using large datasets. Sequential Backward Selection and Principal Component Analysis techniques were used for feature's selection and while the former can produce the better quantum machine learning models in specific cases, it is more unstable. Additionally, we show that such variability in the results is caused by the use of discrete variables, highlighting the suitability of Principal Component analysis transformed data for quantum machine learning applications in the high energy physics context.