Clifford Kolmogorov-Arnold Networks

Authors: Matthias Wolff¹, Francesco Alesiani², Christof Duhme¹, Xiaoyi Jiang^1
1: University of Münster, Department of Computer Science
²: NEC Laboratories Europe GmbH

Link to Paper: https://arxiv.org/abs/2602.05977
This repository contains the codebase to the aforementioned paper and is Work In Progress, as we are still cleaning the code and documenting it better.

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.

Table of Contents

[TBA]

How to use

[TBA]