Effects of noise on the overparametrization of quantum neural networks
Physical Review Research · 18.03.2024 · 6 (1)
DOI: 10.1103/physrevresearch.6.013295 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Research, online erschienen am 18.03.2024. Verfasst von Diego García-Martín und 2 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Department of Energy, Office of Science, Los Alamos National Laboratory.
Abstract (Originalsprache)
Overparametrization is one of the most surprising and notorious phenomena in machine learning. Recently, there have been several efforts to study if, and how, quantum neural networks (QNNs) acting in the absence of hardware noise can be overparametrized. In particular, it has been proposed that a QNN can be defined as overparametrized if it has enough parameters to explore all available directions in state space. That is, if the rank of the quantum Fisher information matrix (QFIM) for the QNN's output state is saturated. Here, we explore how the presence of noise affects the overparametrization phenomenon. Our results show that noise can “turn on” previously zero eigenvalues of the QFIM. This enables the parametrized state to explore directions that were otherwise inaccessible, thus potentially turning an overparametrized QNN into an underparametrized one. For small noise levels, the QNN is quasioverparametrized, as large eigenvalues coexists with small ones. Then, we prove that as the magnitude of noise increases all the eigenvalues of the QFIM become exponentially suppressed, indicating that the state becomes insensitive to any change in the parameters. As such, there is a pull-and-tug effect where noise can enable new directions but also suppress the sensitivity to parameter updates. Finally, our results imply that current QNN capacity measures are ill-defined when hardware noise is present. Published by the American Physical Society 2024
Förderung
- U.S. Department of Energy
- Office of Science
- Los Alamos National Laboratory
- Laboratory Directed Research and Development
Zitieren
APA
García-Martín, D., Larocca, M., & Cerezo, M. (2024). Effects of noise on the overparametrization of quantum neural networks. Physical Review Research, 6(1). https://doi.org/10.1103/physrevresearch.6.013295
Vancouver
García-Martín D, Larocca M, Cerezo M. Effects of noise on the overparametrization of quantum neural networks. Physical Review Research. 2024;6(1). doi:10.1103/physrevresearch.6.013295
BibTeX
@article{GarcaMartn2024,
author = {García-Martín, Diego and Larocca, Martín and Cerezo, M.},
title = {Effects of noise on the overparametrization of quantum neural networks},
journal = {Physical Review Research},
year = {2024},
volume = {6},
number = {1},
doi = {10.1103/physrevresearch.6.013295}
}
EUVIMED