Free-RBF-KAN: Kolmogorov-Arnold Networks with Adaptive Radial Basis Functions for Efficient Function Learning

• URL: http://arxiv.org/abs/2601.07760v2
• Date: Tue, 13 Jan 2026 18:39:13 GMT
• Title: Free-RBF-KAN: Kolmogorov-Arnold Networks with Adaptive Radial Basis Functions for Efficient Function Learning
• Abstract summary: Kolmogorov-Arnold Networks (KANs) have shown strong potential for efficiently approximating complex nonlinear functions.<n>The original KAN formulation relies on B-spline basis functions, which incur substantial computational overhead due to De Boor's algorithm.<n>We propose Free-RBF-KAN, a RBF-based KAN architecture that incorporates adaptive learning grids and trainable smoothness to close this performance gap.
• Score: 2.2851922041620587
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Kolmogorov-Arnold Networks (KANs) have shown strong potential for efficiently approximating complex nonlinear functions. However, the original KAN formulation relies on B-spline basis functions, which incur substantial computational overhead due to De Boor's algorithm. To address this limitation, recent work has explored alternative basis functions such as radial basis functions (RBFs) that can improve computational efficiency and flexibility. Yet, standard RBF-KANs often sacrifice accuracy relative to the original KAN design. In this work, we propose Free-RBF-KAN, a RBF-based KAN architecture that incorporates adaptive learning grids and trainable smoothness to close this performance gap. Our method employs freely learnable RBF shapes that dynamically align grid representations with activation patterns, enabling expressive and adaptive function approximation. Additionally, we treat smoothness as a kernel parameter optimized jointly with network weights, without increasing computational complexity. We provide a general universality proof for RBF-KANs, which encompasses our Free-RBF-KAN formulation. Through a broad set of experiments, including multiscale function approximation, physics-informed machine learning, and PDE solution operator learning, Free-RBF-KAN achieves accuracy comparable to the original B-spline-based KAN while delivering faster training and inference. These results highlight Free-RBF-KAN as a compelling balance between computational efficiency and adaptive resolution, particularly for high-dimensional structured modeling tasks.

Related papers

• Hierarchical RBF-KAN and RBF-SKAN Architectures for Multidimensional Function Approximation and Random Field Learning [0.0]
  We propose and analyze hierarchical Kolmogorov-Arnold neural network architectures employing radial basis functions as activation functions.<n>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 Kolmogorov-Arnold network (hierarchical RBF-SKAN) for random field learning.
  arXiv  Detail & Related papers  (2026-06-01T22:33:53Z)
• Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks [39.58172554437255]
  We introduce a broader family of radial basis kernels and initializing the kernel shape parameter using leave-one-out cross-validation (LOOCV)<n>To the best of our knowledge, this is the first study that integrates LOOCV-based kernel scale estimation with deep KAN training.<n>The proposed adaptive RBF-KAN is evaluated on several two-dimensional benchmark functions.
  arXiv  Detail & Related papers  (2026-05-20T01:28:34Z)
• GRIFDIR: Graph Resolution-Invariant FEM Diffusion Models in Function Spaces over Irregular Domains [56.121725064621295]
  Score-based diffusion models in function spaces offer a principled framework for modelling function-valued data.<n>However, practical implementations have struggled to fully realise these benefits.<n>We propose a novel architecture that represents generalised convolutional kernels as finite graph kernels.
  arXiv  Detail & Related papers  (2026-05-05T08:33:52Z)
• DualFlexKAN: Dual-stage Kolmogorov-Arnold Networks with Independent Function Control [2.071516130824992]
  Kolmogorov-Arnold Networks (KANs) address this limitation through edge-centric learnable functions.<n>KANs suffer from parameter scaling and architectural rigidity that hinders the effective integration of standard regularization techniques.<n>This paper introduces the DualFlexKAN (DFKAN), a flexible architecture featuring a dual-stage mechanism that independently controls pre-linear input transformations and post-linear outputs.
  arXiv  Detail & Related papers  (2026-03-09T16:36:04Z)
• FEKAN: Feature-Enriched Kolmogorov-Arnold Networks [0.34376560669160394]
  Kolmogorov-Arnold Networks (KANs) have emerged as a compelling alternative to multilayer perceptrons.<n>FEKAN is a simple yet effective extension that preserves all the advantages of KAN while improving computational efficiency and predictive accuracy.
  arXiv  Detail & Related papers  (2026-02-18T15:17:55Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• Solving Nonlinear PDEs with Sparse Radial Basis Function Networks [0.0]
  We propose a novel framework for solving nonlinear PDEs using sparse radial basis function (RBF) networks.<n>This work is motivated by longstanding challenges in traditional RBF collocation methods, along with the limitations of physics-informed neural networks (PINNs) and Gaussian process (GP) approaches.
  arXiv  Detail & Related papers  (2025-05-12T17:12:53Z)
• Learning Expressive Random Feature Models via Parametrized Activations [13.5257960837278]
  We introduce the Random Feature Model with Learnable Activation Functions (RFLAF)<n>RFLAF parameterizes activation functions as weighted sums of basis functions within the random feature framework.<n>We show that RFLAFs with learnable activation component largely expand the represented function space.
  arXiv  Detail & Related papers  (2024-11-29T04:38:12Z)
• LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation [64.34935748707673]
  Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. We propose a novel method of Learning Resampling (termed LeRF) which takes advantage of both the structural priors learned by DNNs and the locally continuous assumption. LeRF assigns spatially varying resampling functions to input image pixels and learns to predict the shapes of these resampling functions with a neural network.
  arXiv  Detail & Related papers  (2024-07-13T16:09:45Z)
• Enhancing Kernel Flexibility via Learning Asymmetric Locally-Adaptive Kernels [35.76925787221499]
  This paper introduces the concept of Locally-Adaptive-Bandwidths (LAB) as trainable parameters to enhance the Radial Basis Function (RBF) kernel. The parameters in LAB RBF kernels are data-dependent, and its number can increase with the dataset. This paper for the first time establishes an asymmetric kernel ridge regression framework and introduces an iterative kernel learning algorithm.
  arXiv  Detail & Related papers  (2023-10-08T17:08:15Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  Layer-wise Feedback feedback (LFP) is a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions.<n>Our method then implements a greedy reinforcing approach helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization [73.80101701431103]
  The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in constructing Bayesian neural networks. We study the usefulness of the LLA in Bayesian optimization and highlight its strong performance and flexibility.
  arXiv  Detail & Related papers  (2023-04-17T14:23:43Z)
• Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient [65.08966446962845]
  offline reinforcement learning, which aims at optimizing decision-making strategies with historical data, has been extensively applied in real-life applications. We take a step by considering offline reinforcement learning with differentiable function class approximation (DFA) Most importantly, we show offline differentiable function approximation is provably efficient by analyzing the pessimistic fitted Q-learning algorithm.
  arXiv  Detail & Related papers  (2022-10-03T07:59:42Z)
• A Robust Asymmetric Kernel Function for Bayesian Optimization, with Application to Image Defect Detection in Manufacturing Systems [2.4278445972594525]
  We propose a robust kernel function, Asymmetric Elastic Net Radial Basis Function (AEN-RBF) We show theoretically that AEN-RBF can realize smaller mean squared prediction error under mild conditions. We also show that the AEN-RBF kernel function is less sensitive to outliers.
  arXiv  Detail & Related papers  (2021-09-22T17:59:05Z)
• Compressing Deep ODE-Nets using Basis Function Expansions [105.05435207079759]
  We consider formulations of the weights as continuous-depth functions using linear combinations of basis functions. This perspective allows us to compress the weights through a change of basis, without retraining, while maintaining near state-of-the-art performance. In turn, both inference time and the memory footprint are reduced, enabling quick and rigorous adaptation between computational environments.
  arXiv  Detail & Related papers  (2021-06-21T03:04:51Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.