Metraipolis › archive › dc_7e0d518a4e2a

Classical $\mathrm{SU}(2)$ Models Match or Exceed Shallow Variational Quantum Circuits on Vision Benchmarks — arXiv:2608.07822

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07822
License (as archived)
CC0-1.0
Archived
2026-10-19T08:53:57.763Z
SHA-256 of the archived text
9dfbb578f8ce827e7d81f88c975e5d3e55e4b110349782b9c1757111873fe7ba
Stable URL of this page
https://metraipolis.com/documento/dc_7e0d518a4e2a

How to cite

Classical $\mathrm{SU}(2)$ Models Match or Exceed Shallow Variational Quantum Circuits on Vision Benchmarks — arXiv:2608.07822 — arXiv (en), https://arxiv.org/abs/2608.07822 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e0d518a4e2a (Metraipolis archive dc_7e0d518a4e2a, sha256 9dfbb578f8ce827e7d81f88c975e5d3e55e4b110349782b9c1757111873fe7ba)
BibTeX
@misc{dc7e0d518a4e2a,
  title = {Classical $mathrmSU(2)$ Models Match or Exceed Shallow Variational Quantum Circuits on Vision Benchmarks — arXiv:2608.07822},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07822},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e0d518a4e2a; sha256 9dfbb578f8ce827e7d81f88c975e5d3e55e4b110349782b9c1757111873fe7ba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07822. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from $\mathrm{SU}(2)$ geometry, yet their performance on classical supervised learning remains poorly understood. We compare real-valued, quaternion-valued, and quantum classification heads on identical frozen features across MNIST, FashionMNIST, and CIFAR-10. CIFAR-10 uses a learned 16-dimensional bottleneck and frozen ImageNet-pretrained ResNet18 features to separate architecture from representation quality. Quaternion classifiers match or approach real-valued baselines while outperforming shallow VQCs. On MNIST and FashionMNIST, quaternion networks nearly equal real-valued MLPs, whereas product-state VQCs show lower accuracy and higher cost. On CIFAR-10, quaternion networks retain 94--97% of real-valued performance and remain stable under a 32-fold increase in dimensionality. Product-state circuits underperform quaternion classifiers, while entanglement gives modest grayscale gains but reverses under pretrained CNN features (9.25 pp degradation vs.\ product-state). Fubini--Study/QFI natural gradients improve geometric alignment but not short-horizon loss reduction vs.\ Adam. A Friedman test on five-seed MNIST detects model differences ($\chi^2=12.796$, $p=0.0051$, $n=5$), with Wilcoxon tests yielding large effect sizes ($d>5$) for QuatNet vs.\ quantum comparisons. For FashionMNIST and CIFAR-10, large effects ($d>2.0$) are the primary statistic given $n=3$. These results indicate that quaternion networks provide efficient, stable $\mathrm{SU}(2)$ alternatives to shallow VQCs on tasks lacking intrinsic quantum structure. Shared local $\mathrm{SU}(2)$ geometry and shallow entanglement are insufficient, within the regime studied, to confer practical quantum advantage. Conclusions are limited to shallow, measurement-limited circuits on such tasks.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.PF).
Categorie arXiv: Performance (cs.PF) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.07822 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T08:51:22.486Z dalla pagina https://arxiv.org/catchup/cs.PF/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).