Metraipolis › archive › dc_ce8bef692bc4

What a Reporting Convention Hides: A Matched-Budget Audit of Quantum Natural Gradient with an Exactly Computed Metric — arXiv:2610.09425

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.09425
License (as archived): CC0-1.0
Archived: 2026-10-08T11:56:39.133Z
SHA-256 of the archived text: 56387f4fbd85415223a650efb6b719256a6b65399a041dd614679edb5e4e1734
Stable URL of this page: https://metraipolis.com/documento/dc_ce8bef692bc4

How to cite

What a Reporting Convention Hides: A Matched-Budget Audit of Quantum Natural Gradient with an Exactly Computed Metric — arXiv:2610.09425 — arXiv (en), https://arxiv.org/abs/2610.09425 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce8bef692bc4 (Metraipolis archive dc_ce8bef692bc4, sha256 56387f4fbd85415223a650efb6b719256a6b65399a041dd614679edb5e4e1734)

BibTeX

@misc{dcce8bef692bc4,
  title = {What a Reporting Convention Hides: A Matched-Budget Audit of Quantum Natural Gradient with an Exactly Computed Metric — arXiv:2610.09425},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09425},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce8bef692bc4; sha256 56387f4fbd85415223a650efb6b719256a6b65399a041dd614679edb5e4e1734},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09425. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Several published comparisons of variational quantum optimizers time only runs that reach a target loss, or read the verdict at a single target. Either convention could decide whether an optimizer's costlier steps pay off. We measure how much each convention changes verdicts among Adam, simultaneous perturbation stochastic approximation (SPSA) and quantum natural gradient (QNG), on initializations held out from the selection of settings. We compute the exact metric that preconditions QNG, price every step in circuit evaluations and give every method the same budget. In a median pooled over circuit widths, cost families and a sweep of settings with common misses, SPSA needs more than twice Adam's evaluations to reach a loose target. Dropping the censored runs that miss the target hides this gap. On the global-cost family we hold fixed the settings selected for a strict target. QNG then usually reaches the loose target after Adam but the strict target first. QNG's strict-target lead disappears when the metric's simulator price, linear in the number of parameters, is replaced by an assumed hardware count quadratic in that number. We recommend charging every miss the budget and reporting verdicts across targets.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Quantum Physics (quant-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.09425 — 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 2026-10-08T10:50:37.684Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).