Comparing Classical and Quantum Machine Learning for Regression in High Energy Physics Collision Data
Abstract
The classification and regression of particle collision events constitute a persistent computational challenge in experimental high energy physics, where large volumes of simulated data must be processed with both speed and precision. This work carries out a systematic comparison of four classical machine learning architectures, support vector machines (SVM), artificial neural networks (ANN), convolutional neural networks (CNN), and long short-term memory (LSTM) networks against their quantum counterparts: quantum SVM (QSVM), quantum neural networks (QNN), quantum CNN (QCNN), and quantum LSTM (QLSTM). All models are trained on simulated proton-proton collision events with electron-positron and muon-antimuon final states from the CERN Open Data portal, using transverse-momentum components as input features and transverse-momentum magnitude as the regression target. Classical architectures, and in particular the CNN and LSTM, achieve marginally better quantitative performance under current hardware and dataset constraints. Quantum models, however, reach competitive accuracy with substantially fewer trainable parameters: the QCNN reproduces the performance of the deep classical CNN using only four qubits and a circuit of depth three, pointing to a genuine parameter-efficiency advantage on near-term quantum devices. A baseline analysis confirms that the regression problem is non-trivial for shallow polynomial fits, supporting the relevance of the architectural comparison. These results characterize the trade-offs between classical and quantum approaches under realistic, resource-constrained conditions and provide a benchmark for future studies on actual quantum hardware.
Related
- Comparing classical and quantum QUBO solvers: optimality, trajectory diagnostics, and limits of solver selection
- The ZZ feature map induces a signless Laplacian metric: a closed-form classical surrogate for quantum kernel regression
- Learning nuclear mass systematics with hybrid quantum-classical mixtures of experts
- A hybrid quantum-classical neural network for learning to route
- Witnessing Quantum Bayesian Inference beyond Classical Learning
BibTeX
@misc{mahmood2026comparing,
title = {{Comparing Classical and Quantum Machine Learning for Regression in High Energy Physics Collision Data}},
author = {Tariq Mahmood and Zain ul Abidin and Itzel Luviano Soto and Alfredo Raya},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.28084},
eprint = {2608.28084},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28084},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Comparing Classical and Quantum Machine Learning for Regression in High Energy Physics Collision Data
AU - Tariq Mahmood
AU - Zain ul Abidin
AU - Itzel Luviano Soto
AU - Alfredo Raya
PY - 2026
DA - 2026/08/28
PB - arXiv
DO - 10.48550/arxiv.2608.28084
UR - https://arxiv.org/abs/2608.28084
AB - The classification and regression of particle collision events constitute a persistent computational challenge in experimental high energy physics, where large volumes of simulated data must be processed with both speed and precision. This work carries out a systematic comparison of four classical machine learning architectures, support vector machines (SVM), artificial neural networks (ANN), convolutional neural networks (CNN), and long short-term memory (LSTM) networks against their quantum counterparts: quantum SVM (QSVM), quantum neural networks (QNN), quantum CNN (QCNN), and quantum LSTM (QLSTM). All models are trained on simulated proton-proton collision events with electron-positron and muon-antimuon final states from the CERN Open Data portal, using transverse-momentum components as input features and transverse-momentum magnitude as the regression target. Classical architectures, and in particular the CNN and LSTM, achieve marginally better quantitative performance under current hardware and dataset constraints. Quantum models, however, reach competitive accuracy with substantially fewer trainable parameters: the QCNN reproduces the performance of the deep classical CNN using only four qubits and a circuit of depth three, pointing to a genuine parameter-efficiency advantage on near-term quantum devices. A baseline analysis confirms that the regression problem is non-trivial for shallow polynomial fits, supporting the relevance of the architectural comparison. These results characterize the trade-offs between classical and quantum approaches under realistic, resource-constrained conditions and provide a benchmark for future studies on actual quantum hardware.
ER -