EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Theory for Equivariant Quantum Neural Networks

Quynh T. Nguyen, Louis Schatzki, Paolo Braccia, Michael Ragone, Patrick J. Coles, Frédéric Sauvage, Martín Larocca, M. Cerezo

PRX Quantum · 06.05.2024 · 5 (2)

DOI: 10.1103/prxquantum.5.020328 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PRX Quantum, online erschienen am 06.05.2024. Verfasst von Quynh T. Nguyen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 105-mal zitiert (Crossref) und nennt 113 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Department of Energy, Los Alamos National Laboratory, NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quantum neural network architectures that have little to no inductive biases are known to face trainability and generalization issues. Inspired by a similar problem, recent breakthroughs in machine learning address this challenge by creating models encoding the symmetries of the learning task. This is materialized through the usage of equivariant neural networks the action of which commutes with that of the symmetry. In this work, we import these ideas to the quantum realm by presenting a comprehensive theoretical framework to design equivariant quantum neural networks (EQNNs) for essentially any relevant symmetry group. We develop multiple methods to construct equivariant layers for EQNNs and analyze their advantages and drawbacks. Our methods can find unitary or general equivariant quantum channels efficiently even when the symmetry group is exponentially large or continuous. As a special implementation, we show how standard quantum convolutional neural networks (QCNNs) can be generalized to group-equivariant QCNNs where both the convolution and pooling layers are equivariant to the symmetry group. We then numerically demonstrate the effectiveness of a S U ( 2 ) -equivariant QCNN over symmetry-agnostic QCNN on a classification task of phases of matter in the bond-alternating Heisenberg model. Our framework can be readily applied to virtually all areas of quantum machine learning. Lastly, we discuss about how symmetry-informed models such as EQNNs provide hopes to alleviate central challenges such as barren plateaus, poor local minima, and sample complexity. Published by the American Physical Society 2024

Förderung

  • U.S. Department of Energy
  • Los Alamos National Laboratory
  • NSF
  • Office of Science
  • Office of Advanced Scientific Computing Research
  • Laboratory Directed Research and Development
  • National Science Foundation (NSF) Quantum Leap Challenge Institute

Zitieren

APA

Nguyen, Q. T., Schatzki, L., Braccia, P., Ragone, M., Coles, P. J., Sauvage, F., Larocca, M., & Cerezo, M. (2024). Theory for Equivariant Quantum Neural Networks. PRX Quantum, 5(2). https://doi.org/10.1103/prxquantum.5.020328

Vancouver

Nguyen QT, Schatzki L, Braccia P, Ragone M, Coles PJ, Sauvage F, et al. Theory for Equivariant Quantum Neural Networks. PRX Quantum. 2024;5(2). doi:10.1103/prxquantum.5.020328

BibTeX
@article{Nguyen2024,
  author = {Nguyen, Quynh T. and Schatzki, Louis and Braccia, Paolo and Ragone, Michael and Coles, Patrick J. and Sauvage, Frédéric and Larocca, Martín and Cerezo, M.},
  title = {Theory for Equivariant Quantum Neural Networks},
  journal = {PRX Quantum},
  year = {2024},
  volume = {5},
  number = {2},
  doi = {10.1103/prxquantum.5.020328}
}
Kostenlos starten →