Metraipolis › archive › dc_b73b2b0daeb4

Shallow neural network approximation in mixed Sobolev spaces — arXiv:2609.05263

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05263
License (as archived)
CC0-1.0
Archived
2026-10-16T23:00:13.414Z
SHA-256 of the archived text
6b8c0eaf6f335a947e2c015798875b56819e131113821a031d6d81346dc713a5
Stable URL of this page
https://metraipolis.com/documento/dc_b73b2b0daeb4

How to cite

Shallow neural network approximation in mixed Sobolev spaces — arXiv:2609.05263 — arXiv (en), https://arxiv.org/abs/2609.05263 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b73b2b0daeb4 (Metraipolis archive dc_b73b2b0daeb4, sha256 6b8c0eaf6f335a947e2c015798875b56819e131113821a031d6d81346dc713a5)
BibTeX
@misc{dcb73b2b0daeb4,
  title = {Shallow neural network approximation in mixed Sobolev spaces — arXiv:2609.05263},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05263},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b73b2b0daeb4; sha256 6b8c0eaf6f335a947e2c015798875b56819e131113821a031d6d81346dc713a5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05263. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We investigate the best $L_2$ approximation of mixed Sobolev spaces by shallow neural networks with $n$ neurons and general activation functions. We first establish an activation-independent Fourier-block principle: if an activation has univariate approximation order $\rho$ in the sense of the Fourier-block property, then the global approximation rate has algebraic order $\min\{\alpha,\rho\}$ for target functions of mixed smoothness $\alpha$, up to explicit logarithmic factors. To verify this property for concrete activations, we introduce a structured univariate approximation condition that implies the Fourier-block property with explicit parameters. For $\mathrm{ReLU}^k$, a matching algebraic lower bound identifies $\min\{\alpha,k+1\}$ as the optimal algebraic approximation exponent in any dimension, up to logarithmic factors in the upper bound. The framework also yields the exponent $\min\{\alpha,k+1\}$ for cardinal B-splines and soft-$\mathrm{ReLU}^k$, and the full mixed-smoothness exponent $\alpha$ for ELU and cosine activations, again up to logarithmic~factors.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.LG).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.05263 — 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 2026-10-16T22:31:32.250Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).