Metraipolis › archive › dc_05da0285066d

Minimum-Norm Interpolation in Weighted Variation Spaces: Direct and Inverse Problems — arXiv:2611.01105

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01105
License (as archived)
CC0-1.0
Archived
2026-11-03T18:42:33.713Z
SHA-256 of the archived text
eb6b881ec669b724d37040ccee891f69c1ee756fa4bad94d295e7f0bebfb5209
Stable URL of this page
https://metraipolis.com/documento/dc_05da0285066d

How to cite

Minimum-Norm Interpolation in Weighted Variation Spaces: Direct and Inverse Problems — arXiv:2611.01105 — arXiv (en), https://arxiv.org/abs/2611.01105 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_05da0285066d (Metraipolis archive dc_05da0285066d, sha256 eb6b881ec669b724d37040ccee891f69c1ee756fa4bad94d295e7f0bebfb5209)
BibTeX
@misc{dc05da0285066d,
  title = {Minimum-Norm Interpolation in Weighted Variation Spaces: Direct and Inverse Problems — arXiv:2611.01105},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01105},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_05da0285066d; sha256 eb6b881ec669b724d37040ccee891f69c1ee756fa4bad94d295e7f0bebfb5209},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01105. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study minimum-norm interpolation in weighted variation spaces generated by ReLU$^s$ ridge functions on the unit ball, where $s$ is a positive integer. For a target $f$ in the weighted variation space and a node set with sufficiently small fill distance $h$, every minimum-norm interpolant satisfies the direct bound $\|f-\mathscr{I}_{X_h}f\|_{L_2(\mathbb{B}^d)}\lesssim_{d,s}h^{(2s+1)/4}\|f\|_{\mathcal{V}_s}$. Under a boundary separation condition on the nodes, we construct a matching lower bound for the worst-case interpolation error. For the inverse problem, we introduce dual certificates and derive an estimate analogous to a Bernstein inequality. Under suitable upper bounds on dictionary size and spectral lower bounds for the atomic Gram matrices, sufficiently fast $L_2$ convergence of minimum-norm interpolants along geometrically decreasing fill distances implies that the target belongs to $\mathcal{V}_s$. As a byproduct, the best $L_2$ approximation error $E_n(f)_{L_2(\mathbb{B}^d)}$ for shallow ReLU$^s$ networks of width at most $n$ satisfies $E_n(f)_{L_2(\mathbb{B}^d)}\lesssim_{d,s}n^{-1/2-(2s+1)/(2d)}\|f\|_{\mathcal{V}_s}$, with the weighted atomic cost of an approximating network bounded by a constant multiple of $\|f\|_{\mathcal{V}_s}$, independently of $n$.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.01105 — 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 2026-11-03T18:13:37.687Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).