Metraipolis › archive › dc_acdee2813124

Who can sample forever? Shot noise effects in quantum linear regression — arXiv:2610.12015

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12015
License (as archived)
CC0-1.0
Archived
2026-10-09T06:39:13.643Z
SHA-256 of the archived text
1f8e0668c67801c20cee03ead7b3a1e21f0c3c52229c1ae290b68df5a009f294
Stable URL of this page
https://metraipolis.com/documento/dc_acdee2813124

How to cite

Who can sample forever? Shot noise effects in quantum linear regression — arXiv:2610.12015 — arXiv (en), https://arxiv.org/abs/2610.12015 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_acdee2813124 (Metraipolis archive dc_acdee2813124, sha256 1f8e0668c67801c20cee03ead7b3a1e21f0c3c52229c1ae290b68df5a009f294)
BibTeX
@misc{dcacdee2813124,
  title = {Who can sample forever? Shot noise effects in quantum linear regression — arXiv:2610.12015},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12015},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_acdee2813124; sha256 1f8e0668c67801c20cee03ead7b3a1e21f0c3c52229c1ae290b68df5a009f294},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12015. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Quantum fidelity kernels and quantum extreme learning machines share the same basic architecture: a fixed quantum device generates features that are combined through a classically trained linear model. We refer to this broad non-variational setting as quantum linear regression. A defining aspect of these models is that the quantum features are not directly available, but must be estimated from a finite number of shots. We show that finite statistics makes quantum linear regression unavoidably ill-conditioned. Ideal feature vectors are confined to a subspace determined by the dimension of the Hilbert space, whereas finite-shot estimates generically acquire components outside this subspace. Training then attempts to fit directions that disappear in the infinite-statistics limit, making the learned model increasingly sensitive to sampling noise. We analyze this mechanism for quantum extreme learning machines trained on $n_{\rm tr}$ states with $N$ shots per state. Despite the ill-conditioning, predictions remain controlled when the training targets are exact. Finite sampling produces a systematic prediction error that decreases quadratically with $N$, while fluctuations induced by the random training measurements decrease inversely with the total training budget. Thus, unlike in standard linear regression with exactly known features, increasing the dataset size alone cannot remove the error caused by sampling noise. If the training targets are also noisy, due for instance to state-preparation errors, the otherwise hidden directions become active. The test error can then increase with $N$, a behavior that we ascribe to a form of quantum overfitting. Our results expose a fundamental tradeoff between dataset size and per-state statistics in non-variational quantum learning and provide a baseline for resource-aware training and regularization strategies.

Tema degli esploratori: fisica e astronomia (elenco arXiv quant-ph, nuovi lavori del giorno).
Categorie arXiv: Quantum Physics (quant-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.12015 — 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 2026-10-09T05:58:46.995Z dalla pagina https://arxiv.org/list/quant-ph/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).