Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric
Physical Review Letters · 31.07.2024 · 133 (5)
DOI: 10.1103/physrevlett.133.050603 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Letters, online erschienen am 31.07.2024. Verfasst von Tobias Haug und 1 weiteren Autor:innen. Beteiligte Einrichtung: Quantum Research Center, Technology Innovation Institute, Abu Dhabi, United Arab Emirates. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK Research and Innovation, Engineering and Physical Sciences Research Council, Samsung GRC project.
Abstract (Originalsprache)
Generalization is the ability of machine learning models to make accurate predictions on new data by learning from training data. However, understanding generalization of quantum machine learning models has been a major challenge. Here, we introduce the data quantum Fisher information metric (DQFIM). It describes the capacity of variational quantum algorithms depending on variational ansatz, training data, and their symmetries. We apply the DQFIM to quantify circuit parameters and training data needed to successfully train and generalize. Using the dynamical Lie algebra, we explain how to generalize using a low number of training states. Counterintuitively, breaking symmetries of the training data can help to improve generalization. Finally, we find that out-of-distribution generalization, where training and testing data are drawn from different data distributions, can be better than using the same distribution. Our work provides a useful framework to explore the power of quantum machine learning models. Published by the American Physical Society 2024
Autor:innen und Institutionen
- Quantum Research Center, Technology Innovation Institute, Abu Dhabi, United Arab Emirates.
- Blackett Laboratory, Imperial College London, London SW7 2AZ, United Kingdom.
Förderung
- UK Research and Innovation
- Engineering and Physical Sciences Research Council
- Samsung GRC project
Zitieren
APA
Haug, T., & Kim, M. S. (2024). Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric. Physical Review Letters, 133(5). https://doi.org/10.1103/physrevlett.133.050603
Vancouver
Haug T, Kim MS. Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric. Physical Review Letters. 2024;133(5). doi:10.1103/physrevlett.133.050603
BibTeX
@article{Haug2024,
author = {Haug, Tobias and Kim, M S},
title = {Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric},
journal = {Physical Review Letters},
year = {2024},
volume = {133},
number = {5},
doi = {10.1103/physrevlett.133.050603}
}
EUVIMED