Clifford Kolmogorov-Arnold Networks
Machine Learning
2026-02-06 v1 Artificial Intelligence
Abstract
We introduce Clifford Kolmogorov-Arnold Network (ClKAN), a flexible and efficient architecture for function approximation in arbitrary Clifford algebra spaces. We propose the use of Randomized Quasi Monte Carlo grid generation as a solution to the exponential scaling associated with higher dimensional algebras. Our ClKAN also introduces new batch normalization strategies to deal with variable domain input. ClKAN finds application in scientific discovery and engineering, and is validated in synthetic and physics inspired tasks.
Keywords
Cite
@article{arxiv.2602.05977,
title = {Clifford Kolmogorov-Arnold Networks},
author = {Matthias Wolff and Francesco Alesiani and Christof Duhme and Xiaoyi Jiang},
journal= {arXiv preprint arXiv:2602.05977},
year = {2026}
}
Comments
This work has been submitted to the IEEE for possible publication