Generalization of quantum machine learning models using quantum Fisher information metric
File(s)
Published version
Author(s)
Haug, Tobias
Kim, MS
Type
Journal Article
Abstract
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.
Date Issued
2024-08-02
Date Acceptance
2024-07-03
Citation
Physical Review Letters, 2024, 133 (5)
ISSN
0031-9007
Publisher
American Physical Society
Journal / Book Title
Physical Review Letters
Volume
133
Issue
5
Copyright Statement
Published by the American Physical Society Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.
License URL
Identifier
https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.133.050603
Subjects
DYNAMICS
Physical Sciences
Physics
Physics, Multidisciplinary
Science & Technology
Publication Status
Published
Article Number
050603
Date Publish Online
2024-07-31