arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2510.25781cs.LGcs.AIcs.NAcs.NEmath.NA

Kolmogorov-Arnold网络实践指南

A Practitioner's Guide to Kolmogorov-Arnold Networks

Department of Mathematics, Hong Kong Baptist University(香港 Baptist大学数学系);Institution for Foundations of Data Science, Yale University(数据科学基础研究所,耶鲁大学);Robotics and Technology of Computers Lab., Universidad de Sevilla(机器人与计算机技术实验室,塞维利亚大学)

Amir Noorizadegan, Sifan Wang, Leevan Ling, Juan P. Dominguez-Morales

AI总结:

本文系统综述了受Kolmogorov叠加定理启发的KAN网络,从理论基础、设计轴心(基函数)到最新进展,并提供了实用选择指南和未来方向。

摘要:

Kolmogorov-Arnold网络(KAN)的设计灵感来源于Kolmogorov叠加定理(而非由其决定),已成为MLP的结构化替代方案。本综述对快速扩展的KAN文献进行了系统全面的概述。综述围绕三个核心主题组织:(i)阐明KAN与Kolmogorov叠加理论(KST)、MLP和经典核方法之间的关系;(ii)将基函数作为中心设计轴进行分析;(iii)总结在准确性、效率、正则化和收敛性方面的最新进展。最后,我们提供了实用的“选择你的KAN”指南,并概述了开放的研究挑战和未来方向。随附的GitHub仓库为正在进行的KAN研究提供了结构化参考。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑