Metraipolis › archive › dc_1bd22d71c7ca

Into the danger zone: stable extrapolation in high-dimensional function and operator learning — arXiv:2609.36709

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36709
License (as archived)
CC0-1.0
Archived
2026-10-07T17:32:42.246Z
SHA-256 of the archived text
ccfa1bf5a956d9b49f52dbecc940ee3d187e376c6ef46aac7fc00b6841cf6e00
Stable URL of this page
https://metraipolis.com/documento/dc_1bd22d71c7ca

How to cite

Into the danger zone: stable extrapolation in high-dimensional function and operator learning — arXiv:2609.36709 — arXiv (en), https://arxiv.org/abs/2609.36709 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1bd22d71c7ca (Metraipolis archive dc_1bd22d71c7ca, sha256 ccfa1bf5a956d9b49f52dbecc940ee3d187e376c6ef46aac7fc00b6841cf6e00)
BibTeX
@misc{dc1bd22d71c7ca,
  title = {Into the danger zone: stable extrapolation in high-dimensional function and operator learning — arXiv:2609.36709},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36709},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1bd22d71c7ca; sha256 ccfa1bf5a956d9b49f52dbecc940ee3d187e376c6ef46aac7fc00b6841cf6e00},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36709. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Out-of-distribution (OOD) generalization is a central challenge in scientific machine learning. We study regression problems in which the test distribution differs from the training distribution and ask: under what assumptions on the target function or operator is stable extrapolation possible, and how far beyond the training domain can one extrapolate? Existing theory controls the test error through additive penalties measuring the discrepancy between the training and test distributions. Such guarantees show robustness to small distribution shifts, but can be very pessimistic in comparison to OOD performance observed empirically. We identify classes of holomorphic functions and operators for which the OOD generalization error converges at algebraic rates even in the presence of large distribution shifts. This phenomenon stems from the increasing smoothness of higher-index coordinates, leading to what we term a `blessing of high dimensionality'. For learning with either polynomials, deep neural networks or deep neural operators, we derive explicit rates for arbitrary test measures supported on suitable domains and quantify how the admissible domain depends on the underlying regularity of the function or operator. Our extrapolation guarantees are independent of the test distribution, depending only on its support. We also present a series of numerical experiments across a range of functions and operators that support the main theoretical findings.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.36709 — 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 2026-10-07T16:59:48.508Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).