Metraipolis › archive › dc_25af203dd429

Error bounds in Sobolev norms for approximations with norm constrained ReLU neural networks — arXiv:2609.19937

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19937
License (as archived)
CC0-1.0
Archived
2026-10-10T04:09:18.014Z
SHA-256 of the archived text
34aef91ff3d9d71986bb616d69b12faedbf04522250a4d4a535b72931545e1e8
Stable URL of this page
https://metraipolis.com/documento/dc_25af203dd429

How to cite

Error bounds in Sobolev norms for approximations with norm constrained ReLU neural networks — arXiv:2609.19937 — arXiv (en), https://arxiv.org/abs/2609.19937 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25af203dd429 (Metraipolis archive dc_25af203dd429, sha256 34aef91ff3d9d71986bb616d69b12faedbf04522250a4d4a535b72931545e1e8)
BibTeX
@misc{dc25af203dd429,
  title = {Error bounds in Sobolev norms for approximations with norm constrained ReLU neural networks — arXiv:2609.19937},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19937},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25af203dd429; sha256 34aef91ff3d9d71986bb616d69b12faedbf04522250a4d4a535b72931545e1e8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19937. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent studies have shown that smooth functions can be well approximated by ReLU neural networks with path norm constraint on the weights. We extend these results from uniform approximation to approximation in Sobolev norm. Specifically, we analyze how well Sobolev functions in $W^{n,p}$ can be approximated by neural networks with width $W$, depth $L$ and path norm bounded by $K$, when the approximation error is measured in the $W^{1,p}$-norm. For shallow networks with depth $L=1$, we derive the approximation error bound $\mathcal{O}(\max\{W^{-(n-1)/d}, K^{-(n-1)/(s-n)}\})$, when the smoothness index satisfies $n<s=(d+3)/2$ and the input is $d$-dimensional. For deep networks, we remove the restriction on the smoothness by showing that the approximation bound $\mathcal{O}(K^{-(n-1)/(d+d/p+1)})$ holds if the width $W$ and depth $L$ are sufficiently large.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.19937 — 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 2026-10-10T03:48:18.420Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).