Explicit Construction of Approximate Kolmogorov Superpositions with C2 Smoothness
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918504877260800 |
|---|---|
| author | Song, Lunji Cheng, Zilan Toscano, Juan Diego Wang, Li-Lian |
| author_facet | Song, Lunji Cheng, Zilan Toscano, Juan Diego Wang, Li-Lian |
| contents | We explicitly construct an approximate version of the Kolmogorov superpositions, which is composed of C2-inner and outer functions, and can approximate an arbitrary alpha Holder continuous function with accuracy of N to the power -alpha, where N denotes the number of outer summations. The inner functions are generated by applying suitable translations and dilations to a piecewise C2, strictly increasing function, while the outer functions are constructed rowwise through piecewise C2 interpolation using newly designed shape functions. This novel variant of Kolmogorov superpositions overcomes the wild and pathological behaviors of the inherent single variable functions, but retains the essence of Kolmogorov strategy of exact representation-an objective that Sprecher (Neural Netw. 144(2021)438-442) has actively pursued. We also discuss the implications of this new construction and demonstrate its applicability to related neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04392 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explicit Construction of Approximate Kolmogorov Superpositions with C2 Smoothness Song, Lunji Cheng, Zilan Toscano, Juan Diego Wang, Li-Lian Numerical Analysis 41A46, 65Y10, 68W25, 68Q17 We explicitly construct an approximate version of the Kolmogorov superpositions, which is composed of C2-inner and outer functions, and can approximate an arbitrary alpha Holder continuous function with accuracy of N to the power -alpha, where N denotes the number of outer summations. The inner functions are generated by applying suitable translations and dilations to a piecewise C2, strictly increasing function, while the outer functions are constructed rowwise through piecewise C2 interpolation using newly designed shape functions. This novel variant of Kolmogorov superpositions overcomes the wild and pathological behaviors of the inherent single variable functions, but retains the essence of Kolmogorov strategy of exact representation-an objective that Sprecher (Neural Netw. 144(2021)438-442) has actively pursued. We also discuss the implications of this new construction and demonstrate its applicability to related neural networks. |
| title | Explicit Construction of Approximate Kolmogorov Superpositions with C2 Smoothness |
| topic | Numerical Analysis 41A46, 65Y10, 68W25, 68Q17 |
| url | https://arxiv.org/abs/2508.04392 |