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

Abstract

Current quantum systems have significant limitations affecting the processing of large datasets and high dimensionality typical of high energy physics. In this work, 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.

Unravelling physics beyond the standard model with classical and quantum anomaly detection

“…Quantum ML (QML) has recently been proposed as a new framework offering potential speedups and performance improvements over classical ML [25][26][27][28]. Several QML algorithms, like quantum SVCs (QSVCs) [29][30][31], variational quantum classifiers (VQCs) [30,31], quantum convolutional neural networks [32], or quantum autoencoders [33] have been applied to a wide range of HEP problems [34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50]. With the current methods, quantum algorithms generally achieve a performance similar to their classical counterparts.…”