Kolmogorov-Arnold Networks are a new family of neural network architectures which holds promise for overcoming the curse of dimensionality and has interpretability benefits (arXiv:2404.19756). In this paper, we explore the connection between Kolmogorov Arnold Networks (KANs) with piecewise linear (univariate real) functions and ReLU networks. We provide completely explicit constructions to convert a piecewise linear KAN into a ReLU network and vice versa.
@article{arxiv.2503.01702,
title = {Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks},
author = {Nandi Schoots and Mattia Jacopo Villani and Niels uit de Bos},
journal= {arXiv preprint arXiv:2503.01702},
year = {2025}
}
Comments
accepted to AISTATS 2025; 12 pages including bibliography and appendix