Metraipolis › archive › dc_2fe767df8326

Same Spectrum, Harder First-Order Training: Phase-Locking in Single- versus Multi-Qubit Re-Uploading Circuits — arXiv:2610.21778

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21778
License (as archived)
CC0-1.0
Archived
2026-10-16T10:25:16.322Z
SHA-256 of the archived text
3361b67b71456949889e5298947c3877878591fad347e2eb1b3664bbd20ab592
Stable URL of this page
https://metraipolis.com/documento/dc_2fe767df8326

How to cite

Same Spectrum, Harder First-Order Training: Phase-Locking in Single- versus Multi-Qubit Re-Uploading Circuits — arXiv:2610.21778 — arXiv (en), https://arxiv.org/abs/2610.21778 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fe767df8326 (Metraipolis archive dc_2fe767df8326, sha256 3361b67b71456949889e5298947c3877878591fad347e2eb1b3664bbd20ab592)
BibTeX
@misc{dc2fe767df8326,
  title = {Same Spectrum, Harder First-Order Training: Phase-Locking in Single- versus Multi-Qubit Re-Uploading Circuits — arXiv:2610.21778},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21778},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fe767df8326; sha256 3361b67b71456949889e5298947c3877878591fad347e2eb1b3664bbd20ab592},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21778. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Angle-encoded variational quantum circuits implement truncated Fourier series. For one-dimensional inputs, a single-qubit re-uploading (serial) circuit represents every function that a multi-qubit circuit with the same encoding budget $E$ can; we find that this exchange of width for depth is not free in first-order training. Because its state lives on the Bloch sphere, all parameters of the serial circuit move the state, at each input, along one complex direction, which we call \emph{phase-locking}. We prove that this costs no Fourier direction but leaves no direction to spare: however many parameters it has, the serial circuit has at most $2E+2$ tangent directions, one more than its $2E+1$ Fourier coefficients need, while a two-qubit control with the same encoding budget and model class generically has at least $6E+6$. The cost in training is measured against this control, as the number of runs out of 100 that reach the optimum within a fixed step budget. On an exact loss with flat-spectrum targets the gap grows with $E$; at $E=32$ the serial circuit converges in 3, 53 and 83 runs under gradient descent, Adam and Levenberg--Marquardt, the control in 99, 100 and 100. On three real-world series, at matched parameter counts, the serial circuit reaches the least-squares optimum in at most 9 runs under Adam and in 32 to 93 under Levenberg--Marquardt, the control in at least 98 and in all 100; its held-out error is up to about $1.5$ times that of the control under Adam, but no larger in the typical run under Levenberg--Marquardt.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Quantum Physics (quant-ph) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.21778 — 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 2026-10-16T08:48:02.920Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).