A Practitioner's Guide to Kolmogorov-Arnold Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918525352804352 |
|---|---|
| author | Noorizadegan, Amir Wang, Sifan Ling, Leevan Dominguez-Morales, Juan P. |
| author_facet | Noorizadegan, Amir Wang, Sifan Ling, Leevan Dominguez-Morales, Juan P. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25781 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Practitioner's Guide to Kolmogorov-Arnold Networks Noorizadegan, Amir Wang, Sifan Ling, Leevan Dominguez-Morales, Juan P. Machine Learning Artificial Intelligence Numerical Analysis Neural and Evolutionary Computing 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. |
| title | A Practitioner's Guide to Kolmogorov-Arnold Networks |
| topic | Machine Learning Artificial Intelligence Numerical Analysis Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2510.25781 |