Improving Convergence for Quantum Variational Classifiers Using Weight Re-Mapping

Michael Kölle, Alessandro Giovagnoli, Jonas Stein, Maximilian Mansky, Julian Hager, Claudia Linnhoff-Popien

2023

Abstract

In recent years, quantum machine learning has seen a substantial increase in the use of variational quantum circuits (VQCs). VQCs are inspired by artificial neural networks, which achieve extraordinary performance in a wide range of AI tasks as massively parameterized function approximators. VQCs have already demonstrated promising results, for example, in generalization and the requirement for fewer parameters to train, by utilizing the more robust algorithmic toolbox available in quantum computing. A VQCs’ trainable parameters or weights are usually used as angles in rotational gates and current gradient-based training methods do not account for that. We introduce weight re-mapping for VQCs, to unambiguously map the weights to an interval of length 2π, drawing inspiration from traditional ML, where data rescaling, or normalization techniques have demonstrated tremendous benefits in many circumstances. We employ a set of five functions and evaluate them on the Iris and Wine datasets using variational classifiers as an example. Our experiments show that weight re-mapping can improve convergence in all tested settings. Additionally, we were able to demonstrate that weight re-mapping increased test accuracy for the Wine dataset by 10% over using unmodified weights.

Paper Citation

in Harvard Style

Kölle M., Giovagnoli A., Stein J., Mansky M., Hager J. and Linnhoff-Popien C. (2023). Improving Convergence for Quantum Variational Classifiers Using Weight Re-Mapping. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-623-1, pages 251-258. DOI: 10.5220/0011696300003393

in Bibtex Style

@conference{icaart23,
author={Michael Kölle and Alessandro Giovagnoli and Jonas Stein and Maximilian Mansky and Julian Hager and Claudia Linnhoff-Popien},
title={Improving Convergence for Quantum Variational Classifiers Using Weight Re-Mapping},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2023},
pages={251-258},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011696300003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Improving Convergence for Quantum Variational Classifiers Using Weight Re-Mapping
SN - 978-989-758-623-1
AU - Kölle M.
AU - Giovagnoli A.
AU - Stein J.
AU - Mansky M.
AU - Hager J.
AU - Linnhoff-Popien C.
PY - 2023
SP - 251
EP - 258
DO - 10.5220/0011696300003393