Universal Approximation of Continuous Functionals on Compact Subsets via Linear Measurements and Scalar Nonlinearities
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917244499394560 |
|---|---|
| author | Krylov, Andrey Penkin, Maksim |
| author_facet | Krylov, Andrey Penkin, Maksim |
| contents | We study universal approximation of continuous functionals on compact subsets of products of Hilbert spaces. We prove that any such functional can be uniformly approximated by models that first take finitely many continuous linear measurements of the inputs and then combine these measurements through continuous scalar nonlinearities. We also extend the approximation principle to maps with values in a Banach space, yielding finite-rank approximations. These results provide a compact-set justification for the common ``measure, apply scalar nonlinearities, then combine'' design pattern used in operator learning and imaging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03290 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Universal Approximation of Continuous Functionals on Compact Subsets via Linear Measurements and Scalar Nonlinearities Krylov, Andrey Penkin, Maksim Machine Learning Functional Analysis I.2.6 We study universal approximation of continuous functionals on compact subsets of products of Hilbert spaces. We prove that any such functional can be uniformly approximated by models that first take finitely many continuous linear measurements of the inputs and then combine these measurements through continuous scalar nonlinearities. We also extend the approximation principle to maps with values in a Banach space, yielding finite-rank approximations. These results provide a compact-set justification for the common ``measure, apply scalar nonlinearities, then combine'' design pattern used in operator learning and imaging. |
| title | Universal Approximation of Continuous Functionals on Compact Subsets via Linear Measurements and Scalar Nonlinearities |
| topic | Machine Learning Functional Analysis I.2.6 |
| url | https://arxiv.org/abs/2602.03290 |