Metraipolis › archive › dc_285af5df5ed2

Resolution-Consistent Greedy Neural Approximation on Infinite-Dimensional Spaces — arXiv:2608.20812

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20812
License (as archived)
CC0-1.0
Archived
2026-10-18T10:31:05.681Z
SHA-256 of the archived text
e5a10f2425da7b17a6672fc062eaed3fc1a1a2d5c5868a8e5da2b4b7f5d51cd9
Stable URL of this page
https://metraipolis.com/documento/dc_285af5df5ed2

How to cite

Resolution-Consistent Greedy Neural Approximation on Infinite-Dimensional Spaces — arXiv:2608.20812 — arXiv (en), https://arxiv.org/abs/2608.20812 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_285af5df5ed2 (Metraipolis archive dc_285af5df5ed2, sha256 e5a10f2425da7b17a6672fc062eaed3fc1a1a2d5c5868a8e5da2b4b7f5d51cd9)
BibTeX
@misc{dc285af5df5ed2,
  title = {Resolution-Consistent Greedy Neural Approximation on Infinite-Dimensional Spaces — arXiv:2608.20812},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20812},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_285af5df5ed2; sha256 e5a10f2425da7b17a6672fc062eaed3fc1a1a2d5c5868a8e5da2b4b7f5d51cd9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20812. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We develop constructive approximation and learning guarantees for shallow neural models with infinite-dimensional inputs observed through finitely many coordinates. The analysis is based on a parameter-normalized neural dictionary and its associated weighted variation class. Within this class, the approximation error separates into a distribution-dependent coordinate-truncation term and a greedy finite-width term. For empirical regression, a fully-corrective greedy procedure yields population guarantees whose statistical complexity is uniform in the retained input resolution. The same framework extends to Hilbert-valued responses without an explicit dependence on the output dimension. The dimension-free statements are statistical, not computational: selecting a new neuron still requires solving a nonconvex parameter-search problem. The quasi-Polish construction underlying recent infinite-dimensional universal approximation results provides a motivating example, and synthetic experiments illustrate the predicted resolution, width, and sample-size regimes.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Functional Analysis (math.FA).
Pagina del lavoro: https://arxiv.org/abs/2608.20812 — 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 2026-10-18T10:27:55.941Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).