cs.LGJun 1, 2026

Hierarchical RBF-KAN and RBF-SKAN Architectures for Multidimensional Function Approximation and Random Field Learning

Authors: Mingtao XiaQijing Shen

Organizations: University of Houston, Philip Guthrie Hoffman Hall, 3551 Cullen Blvd, Houston, 77204, Texas, United States of America · University of Birmingham, Watson Building, Birmingham, B15 2TT,, United Kingdom · University of Oxford, Henry Wellcome Building for Molecular Physiology, Old Road, Oxford, OX3 7BN, Oxfordshire, United Kingdom

Abstract

In this manuscript, we propose and analyze hierarchical Kolmogorov--Arnold neural network architectures employing radial basis functions as activation functions for approximating deterministic functions and random field models. Specifically, we develop a hierarchical radial-basis-function Kolmogorov--Arnold network (hierarchical RBF-KAN) for multidimensional deterministic function approximation and a hierarchical radial-basis-function stochastic Kolmogorov--Arnold network (hierarchical RBF-SKAN) for random field learning. From a theoretical perspective, we establish universal approximation results for both architectures. In particular, we derive quantitative approximation estimates for the hierarchical RBF-KAN, showing that the proposed framework has the potential to partially alleviate the curse of dimensionality in learning high-dimensional functions by reducing the effective dimensionality of the approximation problem. Furthermore, we show that the hierarchical RBF-SKAN can approximate random field models under the Wasserstein-2 metric. Empirically, we show that our proposed radial-basis-function-based neural network structure could effectively learn multivariate functions and random field models.

Explore similar work

CardsList
  1. Clifford Kolmogorov-Arnold Networks

    Feb 5, 2026Matthias Wolff, Francesco Alesiani, Christof Duhme +1Kolmogorov-Arnold NetworksEquivariant Neural Networks