Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.15922 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909559285612544 |
|---|---|
| author | El-Boukkouri, Fatima-Zahrae Garnier, Josselin Roustant, Olivier |
| author_facet | El-Boukkouri, Fatima-Zahrae Garnier, Josselin Roustant, Olivier |
| contents | In this paper, we consider the reproducing property in Reproducing Kernel Hilbert Spaces (RKHS). We establish a reproducing property for the closure of the class of combinations of composition operators under minimal conditions. This allows to revisit the sufficient conditions for the reproducing property to hold for the derivative operator, as well as for the existence of the mean embedding function. These results provide a framework of application of the representer theorem for regularized learning algorithms that involve data for function values, gradients, or any other operator from the considered class. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15922 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | General reproducing properties in RKHS with application to derivative and integral operators El-Boukkouri, Fatima-Zahrae Garnier, Josselin Roustant, Olivier Statistics Theory Machine Learning In this paper, we consider the reproducing property in Reproducing Kernel Hilbert Spaces (RKHS). We establish a reproducing property for the closure of the class of combinations of composition operators under minimal conditions. This allows to revisit the sufficient conditions for the reproducing property to hold for the derivative operator, as well as for the existence of the mean embedding function. These results provide a framework of application of the representer theorem for regularized learning algorithms that involve data for function values, gradients, or any other operator from the considered class. |
| title | General reproducing properties in RKHS with application to derivative and integral operators |
| topic | Statistics Theory Machine Learning |
| url | https://arxiv.org/abs/2503.15922 |