Input Convex Kolmogorov Arnold Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Deschatre, Thomas, Warin, Xavier
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914316817530880
author Deschatre, Thomas
Warin, Xavier
author_facet Deschatre, Thomas
Warin, Xavier
contents This article presents an input convex neural network architecture using Kolmogorov-Arnold networks (ICKAN). Two specific networks are presented: the first is based on a low-order, linear-by-part, representation of functions, and a universal approximation theorem is provided. The second is based on cubic splines, for which only numerical results support convergence. We demonstrate on simple tests that these networks perform competitively with classical input convex neural networks (ICNNs). In a second part, we use the networks to solve some optimal transport problems needing a convex approximation of functions and demonstrate their effectiveness. Comparisons with ICNNs show that cubic ICKANs produce results similar to those of classical ICNNs.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21208
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Input Convex Kolmogorov Arnold Networks
Deschatre, Thomas
Warin, Xavier
Machine Learning
Optimization and Control
68T07
This article presents an input convex neural network architecture using Kolmogorov-Arnold networks (ICKAN). Two specific networks are presented: the first is based on a low-order, linear-by-part, representation of functions, and a universal approximation theorem is provided. The second is based on cubic splines, for which only numerical results support convergence. We demonstrate on simple tests that these networks perform competitively with classical input convex neural networks (ICNNs). In a second part, we use the networks to solve some optimal transport problems needing a convex approximation of functions and demonstrate their effectiveness. Comparisons with ICNNs show that cubic ICKANs produce results similar to those of classical ICNNs.
title Input Convex Kolmogorov Arnold Networks
topic Machine Learning
Optimization and Control
68T07
url https://arxiv.org/abs/2505.21208