Towards understanding the power of quantum kernels in the NISQ era

by   Xinbiao Wang, et al.

A key problem in the field of quantum computing is understanding whether quantum machine learning (QML) models implemented on noisy intermediate-scale quantum (NISQ) machines can achieve quantum advantages. Recently, Huang et al. [arXiv:2011.01938] partially answered this question by the lens of quantum kernel learning. Namely, they exhibited that quantum kernels can learn specific datasets with lower generalization error over the optimal classical kernel methods. However, most of their results are established on the ideal setting and ignore the caveats of near-term quantum machines. To this end, a crucial open question is: does the power of quantum kernels still hold under the NISQ setting? In this study, we fill this knowledge gap by exploiting the power of quantum kernels when the quantum system noise and sample error are considered. Concretely, we first prove that the advantage of quantum kernels is vanished for large size of datasets, few number of measurements, and large system noise. With the aim of preserving the superiority of quantum kernels in the NISQ era, we further devise an effective method via indefinite kernel learning. Numerical simulations accord with our theoretical results. Our work provides theoretical guidance of exploring advanced quantum kernels to attain quantum advantages on NISQ devices.



There are no comments yet.


page 1

page 2

page 3

page 4


Training Quantum Embedding Kernels on Near-Term Quantum Computers

Kernel methods are a cornerstone of classical machine learning. The idea...

Quantum Multiple Kernel Learning

Kernel methods play an important role in machine learning applications d...

Accelerating variational quantum algorithms with multiple quantum processors

Variational quantum algorithms (VQAs) have the potential of utilizing ne...

Quantum circuit architecture search: error mitigation and trainability enhancement for variational quantum solvers

Quantum error mitigation techniques are at the heart of quantum computat...

Importance of Kernel Bandwidth in Quantum Machine Learning

Quantum kernel methods are considered a promising avenue for applying qu...

Theory of Quantum Generative Learning Models with Maximum Mean Discrepancy

The intrinsic probabilistic nature of quantum mechanics invokes endeavor...

Quantum kernels for real-world predictions based on electronic health records

In recent years, research on near-term quantum machine learning has expl...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.