Metraipolis › archive › dc_21707a65cb89
A Theory of Finite-Noise Optima and Generalization in Quantum Machine Learning — arXiv:2608.24229
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.24229
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:36:52.456Z
- SHA-256 of the archived text
373a406024203fe8467ba8c645a6364dbf1288ab153099de15d57ab9a599bffc- Stable URL of this page
https://metraipolis.com/documento/dc_21707a65cb89
How to cite
A Theory of Finite-Noise Optima and Generalization in Quantum Machine Learning — arXiv:2608.24229 — arXiv (en), https://arxiv.org/abs/2608.24229 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_21707a65cb89 (Metraipolis archive dc_21707a65cb89, sha256 373a406024203fe8467ba8c645a6364dbf1288ab153099de15d57ab9a599bffc)
BibTeX
@misc{dc21707a65cb89,
title = {A Theory of Finite-Noise Optima and Generalization in Quantum Machine Learning — arXiv:2608.24229},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.24229},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_21707a65cb89; sha256 373a406024203fe8467ba8c645a6364dbf1288ab153099de15d57ab9a599bffc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24229. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Quantum noise is expected to degrade quantum machine learning by driving circuits away from their noiseless implementations. Yet recent studies show moderate noise can reduce testing error, a behavior unexplained by weak-noise perturbative error accumulation or strong-noise trainability collapse. Here we develop a statistical learning theory connecting microscopic noise processes to macroscopic learning performance. At its heart is a noise-order purity parameter, derived from a surrogate model analysis, that predicts the noise-induced reduction in model complexity and the consequent reduction in the generalization gap. Noise simultaneously increases prediction bias. Their competition explains the intermediate-noise regime left open between these limits. It produces a finite-noise optimum whose location depends on the learning setup and can disappear in the large-sample limit. Numerical experiments validate these predictions. Noise programming can move a model towards this optimum. These results make the non-monotonic effect of noise predictable and provide a route to harness it. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG). Categorie arXiv: Quantum Physics (quant-ph) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.24229 — 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 2026-10-18T06:28:52.345Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).