Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Kernel Learning by Quantum Annealer. |
| Συγγραφείς: |
Hasegawa, Yasushi, Oshiyama, Hiroki, Ohzeki, Masayuki |
| Πηγή: |
Journal of the Physical Society of Japan; 7/15/2026, Vol. 95 Issue 7, p1-8, 8p |
| Περίληψη: |
The Boltzmann machine is one of the various applications using a quantum annealer. As a feasibility study, we propose an application of the Boltzmann machine to the kernel matrix used in various machine learning techniques. We focus on the fact that shift-invariant kernel functions can be expressed in terms of the expected value of a spectral distribution by the Fourier transformation. Using this transformation, the random Fourier feature (RFF) samples the frequencies and approximates the kernel function. Furthermore, this paper proposes a method to obtain a spectral distribution suitable for the data using a Boltzmann machine. Across Fashion MNIST binary tasks, our approach achieves top or comparable accuracy to a tuned Gaussian RFF and Random Kitchen Sinks with Implicit Kernel Learning, while consistently attaining lower loss and learning bimodal, data-adaptive spectral distributions. On synthetic data (d = 10), it improves test accuracy by +2.8 points over Gaussian RFF. These results indicate that our method remains valuable even when accuracy saturates, by yielding better kernel alignment and richer spectral structure, and it is practically enabled by fast sampling on a quantum annealer. [ABSTRACT FROM AUTHOR] |
|
Copyright of Journal of the Physical Society of Japan is the property of Physical Society of Japan and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Βάση Δεδομένων: |
Complementary Index |