Structural risk minimization for quantum linear classifiers

22Citations
Citations of this article
24Readers
Mendeley users who have this article in their library.

Abstract

Quantum machine learning (QML) models based on parameterized quantum circuits are often highlighted as candidates for quantum computing’s near-term “killer application”. However, the understanding of the empirical and generalization performance of these models is still in its infancy. In this paper we study how to balance between training accuracy and generalization performance (also called structural risk minimization) for two prominent QML models introduced by Havlíček et al. [1], and Schuld and Killoran [2]. Firstly, using relationships to well understood classical models, we prove that two model parameters – i.e., the dimension of the sum of the images and the Frobenius norm of the observables used by the model – closely control the models’ complexity and therefore its generalization performance. Secondly, using ideas inspired by process tomography, we prove that these model parameters also closely control the models’ ability to capture correlations in sets of training examples. In summary, our results give rise to new options for structural risk minimization for QML models.

References Powered by Scopus

Variational quantum algorithms

1602Citations
N/AReaders
Get full text

The theory of variational hybrid quantum-classical algorithms

1460Citations
N/AReaders
Get full text

The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network

951Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Quantum machine learning beyond kernel methods

97Citations
N/AReaders
Get full text

Out-of-distribution generalization for learning quantum dynamics

36Citations
N/AReaders
Get full text

Exponential concentration in quantum kernel methods

18Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Gyurik, C., van Vreumingen, D., & Dunjko, V. (2023). Structural risk minimization for quantum linear classifiers. Quantum, 7. https://doi.org/10.22331/q-2023-01-13-893

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 7

54%

Researcher 4

31%

Lecturer / Post doc 2

15%

Readers' Discipline

Tooltip

Computer Science 7

54%

Physics and Astronomy 5

38%

Engineering 1

8%

Article Metrics

Tooltip
Social Media
Shares, Likes & Comments: 34

Save time finding and organizing research with Mendeley

Sign up for free