Metraipolis › archive › dc_d59222fe8ea5

Gaussian Universality and Its Breakdown in Tensor-Network Machine Learning — arXiv:2610.06080

Source
arXiv
Original
https://arxiv.org/abs/2610.06080
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:27.546Z
SHA-256 of the archived text
60cc2318fea6145f2fb3817995cd3c9fa5c752bbde5048081aa6f1d412cb5c79
Stable URL of this page
https://metraipolis.com/documento/dc_d59222fe8ea5

How to cite

Gaussian Universality and Its Breakdown in Tensor-Network Machine Learning — arXiv:2610.06080 — arXiv, https://arxiv.org/abs/2610.06080 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d59222fe8ea5 (Metraipolis archive dc_d59222fe8ea5, sha256 60cc2318fea6145f2fb3817995cd3c9fa5c752bbde5048081aa6f1d412cb5c79)
BibTeX
@misc{dcd59222fe8ea5,
  title = {Gaussian Universality and Its Breakdown in Tensor-Network Machine Learning — arXiv:2610.06080},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06080},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d59222fe8ea5; sha256 60cc2318fea6145f2fb3817995cd3c9fa5c752bbde5048081aa6f1d412cb5c79},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06080. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Gaussian-process limits are powerful in describing overparameterized machine learning models, yet their validity in structured tensor-network architectures remains unclear. Here we analytically present a moment-based approach that identifies precise conditions for the emergence and breakdown of Gaussian universality in tensor-network learning models, with a focus on matrix product states. We prove that in the large bond dimension limit, the learning models with both local and global observables converge to Gaussian processes, with explicit finite-size bounds on higher-order moment deviations. Whereas in the large physical dimension limit, the Gaussian universality no longer persists: while the models with local observables retain Gaussian-process behavior, those global cases exhibit persistent non-Gaussian corrections. Our results reveal that Gaussian-process behavior in tensor-network learning is controlled not only by parameter number, but also by architectural scaling, observable locality, and the spectral properties.

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/2610.06080 — 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 2026-10-06T05:27:06.027Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).