A Practitioner's Guide to Kolmogorov-Arnold Networks

Abstract

Kolmogorov-Arnold Networks (KANs), whose design is inspired-rather than dictated-by the Kolmogorov superposition theorem, have emerged as a structured alternative to MLPs. This review provides a systematic and comprehensive overview of the rapidly expanding KAN literature. The review is organized around three core themes: (i) clarifying the relationships between KANs and Kolmogorov superposition theory (KST), MLPs, and classical kernel methods; (ii) analyzing basis functions as a central design axis; and (iii) summarizing recent advances in accuracy, efficiency, regularization, and convergence. Finally, we provide a practical "Choose-Your-KAN" guide and outline open research challenges and future directions. The accompanying GitHub repository serves as a structured reference for ongoing KAN research.

References in corpus (16)

• A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems
• Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations
• Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
• Tackling the Curse of Dimensionality with Physics-Informed Neural Networks
• A Survey on Kolmogorov-Arnold Network
• KAN-ODEs: Kolmogorov-Arnold Network Ordinary Differential Equations for Learning Dynamical Systems and Hidden Physics
• Functional Multi-Layer Perceptron: a Nonlinear Tool for Functional Data Analysis
• Multilevel domain decomposition-based architectures for physics-informed neural networks
• Adaptive Training of Grid-Dependent Physics-Informed Kolmogorov-Arnold Networks
• KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Search
• Partition of unity interpolation using stable kernel-based techniques
• Approximation of Eigenfunctions in Kernel-based Spaces
• Power-Enhanced Residual Network for Function Approximation and Physics-Informed Inverse Problems
• FC-KAN: Function Combinations in Kolmogorov-Arnold Networks