Metraipolis › archive › dc_af8a9d1d15dd
Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias — arXiv:2610.21480
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21480
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:22:31.241Z
- SHA-256 of the archived text
2e8122a4ce5f0493b8ad61c1d719072d6a203eae789d478e277835c076e3d3bc- Stable URL of this page
https://metraipolis.com/documento/dc_af8a9d1d15dd
How to cite
Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias — arXiv:2610.21480 — arXiv (en), https://arxiv.org/abs/2610.21480 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af8a9d1d15dd (Metraipolis archive dc_af8a9d1d15dd, sha256 2e8122a4ce5f0493b8ad61c1d719072d6a203eae789d478e277835c076e3d3bc)
BibTeX
@misc{dcaf8a9d1d15dd,
title = {Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias — arXiv:2610.21480},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21480},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af8a9d1d15dd; sha256 2e8122a4ce5f0493b8ad61c1d719072d6a203eae789d478e277835c076e3d3bc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21480. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Kolmogorov-Arnold networks (KANs) have a dimension-independent approximation exponent when the target admits a sufficiently smooth representation by univariate edge functions. We ask whether this favorable scaling belongs to the architecture or to the assumed target class. For arbitrary-depth standard spline-KANs, we prove a worst-case lower bound on isotropic Sobolev balls: below a dimension-independent accuracy threshold, the required number of spline coefficients grows at least exponentially with input dimension. Existing composition-matched MLP results, by contrast, show that favorable exponents on low-arity targets are not exclusive to KANs. We also revisit empirical comparisons. On four scaling-law targets, spline-KAN approximants constructed from known decompositions transfer exactly to MLPs with the cubic ReLU activation $\sigma(x)=(\max\{0,x\})^3$, although their full dense parameter counts are larger. In controlled ridge-profile scans, KANs have a strong advantage when each nonlinear component depends on one input coordinate. When a component couples multiple input coordinates, this advantage may narrow sharply. At tight budgets, interacting targets often favor MLPs. In the random-label test on MNIST, ReLU-MLPs fit the randomized training labels more efficiently than spline-only KANs. Together, these results locate favorable scaling in target structure and a compatible inductive bias, not a general KAN-specific escape from the curse of dimensionality.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.21480 — 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 2026-10-16T08:48:02.722Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).