Metraipolis › archive › dc_f5cde9704cfd
SPSA Hyperparameter Tuning for Variational Quantum Natural Language Inference — arXiv:2608.16939
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16939
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:48:52.588Z
- SHA-256 of the archived text
ef9c103287feca45b571f55f779fb264fd93745a3ce17a48fd2ff74f378a6e43- Stable URL of this page
https://metraipolis.com/documento/dc_f5cde9704cfd
How to cite
SPSA Hyperparameter Tuning for Variational Quantum Natural Language Inference — arXiv:2608.16939 — arXiv (en), https://arxiv.org/abs/2608.16939 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5cde9704cfd (Metraipolis archive dc_f5cde9704cfd, sha256 ef9c103287feca45b571f55f779fb264fd93745a3ce17a48fd2ff74f378a6e43)
BibTeX
@misc{dcf5cde9704cfd,
title = {SPSA Hyperparameter Tuning for Variational Quantum Natural Language Inference — arXiv:2608.16939},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16939},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5cde9704cfd; sha256 ef9c103287feca45b571f55f779fb264fd93745a3ce17a48fd2ff74f378a6e43},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16939. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Training variational quantum models requires choosing between parameter-shift gradients, which are exact but cost $O(P)$ forward evaluations, and simultaneous perturbation stochastic approximation (SPSA), which uses only two samples but produces high-variance estimates that can degrade optimisation on small supervised tasks. Whether the cheap gradient is usable depends on the variance that results from different choices of the SPSA perturbation scale, learning rate, and gain-decay schedule. We varied those quantities across a broad grid on a 6-qubit, 60-parameter QNLI classifier and compared the best configurations to parameter-shift AdamW and BuresQNG. AdamW-style SPSA with $c_0=0.01$, $\eta=0.10$, $\gamma=0.10$ reached $55\% \pm 11\%$ test accuracy, improving over the default configuration ($49\% \pm 6\%$) but remaining 16-19 percentage points below the parameter-shift baselines because the two-sample SPSA gradient estimate has too much variance for reliable optimisation of 60 parameters in 40 epochs. Classical-gain SPSA and Bures-preconditioned SPSA performed worse, at $51\%$ and $46\%$ respectively. Bures-preconditioning a noisy two-sample SPSA gradient amplifies perturbation noise. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG). Categorie arXiv: Quantum Physics (quant-ph) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.16939 — 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 2026-10-18T14:47:59.435Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).