Metraipolis › archive › dc_edce46470a22
Kolmogorov-Arnold Classifier Systems as Universal Approximators — arXiv:2609.37958
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37958
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:31:56.698Z
- SHA-256 of the archived text
be3c9946121744d82f30142017ca247072d41731e413f12b77df9469cb24fbab- Stable URL of this page
https://metraipolis.com/documento/dc_edce46470a22
How to cite
Kolmogorov-Arnold Classifier Systems as Universal Approximators — arXiv:2609.37958 — arXiv (en), https://arxiv.org/abs/2609.37958 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edce46470a22 (Metraipolis archive dc_edce46470a22, sha256 be3c9946121744d82f30142017ca247072d41731e413f12b77df9469cb24fbab)
BibTeX
@misc{dcedce46470a22,
title = {Kolmogorov-Arnold Classifier Systems as Universal Approximators — arXiv:2609.37958},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37958},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edce46470a22; sha256 be3c9946121744d82f30142017ca247072d41731e413f12b77df9469cb24fbab},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37958. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As the input dimension $n$ grows, rule-based machine learning, such as Learning Classifier Systems (LCSs), faces a fundamental scalability bottleneck for function approximation: both rule count and parameter count grow exponentially with $n$. Traditional LCSs partition the $n$-dimensional input space directly, requiring $\mathcal{O}(m^n)$ rules for adequate coverage, where $m$ is the per-variable resolution. This article breaks from this paradigm by reorganizing rules dimension-wise, guided by the Kolmogorov-Arnold representation theorem: any continuous $n$-dimensional function can be expressed as a finite superposition of one-dimensional functions. The proposed Kolmogorov-Arnold Classifier System (KACS) decomposes the target function into one-dimensional subproblems and assigns a dedicated ruleset to each, reducing the worst-case rule count from $\mathcal{O}(m^n)$ to $\mathcal{O}(mn^2)$ and replacing $n$-dimensional local models with one-dimensional models requiring only two parameters per rule, independent of $n$. We also provide the first constructive proof that an LCS, namely KACS, is a universal approximator for continuous functions on compact domains. Evaluated against a direct $n$-dimensional input space partitioning approach under otherwise identical conditions, KACS achieves competitive accuracy in many settings while using only 2\% to 40\% of the parameters. Our implementation is available at this https URL .
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2609.37958 — 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 2026-10-07T16:59:48.402Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).