Introducing Reduced-Width QNNs, an AI-Inspired Ansatz Design Pattern

Jonas Stein, Jonas Stein, Tobias Rohe, Francesco Nappi, Julian Hager, David Bucher, Maximilian Zorn, Michael Kölle, Claudia Linnhoff-Popien

2024

Abstract

Variational Quantum Algorithms are one of the most promising candidates to yield the first industrially relevant quantum advantage. Being capable of arbitrary function approximation, they are often referred to as Quantum Neural Networks (QNNs) when being used in analog settings as classical Artificial Neural Networks (ANNs). Similar to the early stages of classical machine learning, known schemes for efficient architectures of these networks are scarce. Exploring beyond existing design patterns, we propose a reduced-width circuit ansatz design, which is motivated by recent results gained in the analysis of dropout regularization in QNNs. More precisely, this exploits the insight, that the gates of overparameterized QNNs can be pruned substantially until their expressibility decreases. The results of our case study show, that the proposed design pattern can significantly reduce training time while maintaining the same result quality as the standard "full-width" design in the presence of noise. We thus argue, that quantum architecture search should not blindly follow the classical overparameterization trend.

Paper Citation

in Harvard Style

Stein J., Rohe T., Nappi F., Hager J., Bucher D., Zorn M., Kölle M. and Linnhoff-Popien C. (2024). Introducing Reduced-Width QNNs, an AI-Inspired Ansatz Design Pattern. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 1127-1134. DOI: 10.5220/0012449800003636

in Bibtex Style

@conference{icaart24,
author={Jonas Stein and Tobias Rohe and Francesco Nappi and Julian Hager and David Bucher and Maximilian Zorn and Michael Kölle and Claudia Linnhoff-Popien},
title={Introducing Reduced-Width QNNs, an AI-Inspired Ansatz Design Pattern},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={1127-1134},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012449800003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Introducing Reduced-Width QNNs, an AI-Inspired Ansatz Design Pattern
SN - 978-989-758-680-4
AU - Stein J.
AU - Rohe T.
AU - Nappi F.
AU - Hager J.
AU - Bucher D.
AU - Zorn M.
AU - Kölle M.
AU - Linnhoff-Popien C.
PY - 2024
SP - 1127
EP - 1134
DO - 10.5220/0012449800003636
PB - SciTePress