Metraipolis › archive › dc_554c3a160be0
SW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials — arXiv:2610.00050
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00050
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:07:27.099Z
- SHA-256 of the archived text
62c545edaa3baa1a54430c99fa5e5fe6762278b2cb4ae01159ad64c2fd7a3581- Stable URL of this page
https://metraipolis.com/documento/dc_554c3a160be0
How to cite
SW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials — arXiv:2610.00050 — arXiv (en), https://arxiv.org/abs/2610.00050 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_554c3a160be0 (Metraipolis archive dc_554c3a160be0, sha256 62c545edaa3baa1a54430c99fa5e5fe6762278b2cb4ae01159ad64c2fd7a3581)
BibTeX
@misc{dc554c3a160be0,
title = {SW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials — arXiv:2610.00050},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00050},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_554c3a160be0; sha256 62c545edaa3baa1a54430c99fa5e5fe6762278b2cb4ae01159ad64c2fd7a3581},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00050. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Kolmogorov-Arnold Networks (KANs) represent a paradigmatic shift in deep learning by replacing fixed node activations with learnable univariate functions on edges, offering enhanced interpretability and parameter efficiency. While recent polynomial-based KAN variants have addressed the computational overhead of original B-spline implementations, they introduce a fundamental yet underexplored challenge: the domain mismatch between unbounded real-valued inputs and the bounded or semi-infinite support of orthogonal polynomial bases. To address this limitation, we propose the Stieltjes-Wigert Kolmogorov-Arnold Network (SW-KAN), a novel architecture that employs Stieltjes-Wigert q-orthogonal polynomials defined on the semi-infinite domain (0, infinity). We introduce a smooth exponential-of-tanh mapping that stably bridges the domain gap while preserving well-conditioned gradients, and leverage a numerically stable three-term recurrence that evaluates polynomial expansions in O(N) operations without special-function calls. Through comprehensive experiments spanning image classification and continuous function approximation, we demonstrate that SW-KAN achieves superior accuracy-efficiency trade-offs across diverse tasks. The log-normal weight structure and learnable q-parameter of Stieltjes-Wigert polynomials provide a distinct inductive bias that enables robust performance under resource-constrained conditions, including reduced feature dimensionality and limited training data. The proposed architecture not only outperforms established polynomial KAN baselines on standard benchmarks but also exhibits strong representational capacity for approximating complex multivariate functions with remarkably few parameters, making it a compelling alternative for efficient function approximation and classification in resource-constrained settings. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.00050 — 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 2026-10-06T10:21:28.011Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).