On recovering the Radon-Nikodym derivative under the big data assumption
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_ | 1866915612459008000 |
|---|---|
| author | Myleiko, Hanna Solodky, Sergei |
| author_facet | Myleiko, Hanna Solodky, Sergei |
| contents | The present paper is focused on the problem of recovering the Radon-Nikodym derivative under the big data assumption. To address the above problem, we design an algorithm that is a combination of the Nyström subsampling and the standard Tikhonov regularization. The convergence rate of the corresponding algorithm is established both in the case when the Radon-Nikodym derivative belongs to RKHS and in the case when it does not. We prove that the proposed approach not only ensures the order of accuracy as algorithms based on the whole sample size, but also allows to achieve subquadratic computational costs in the number of observations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03891 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On recovering the Radon-Nikodym derivative under the big data assumption Myleiko, Hanna Solodky, Sergei Numerical Analysis 65J20, 65R30 (Primary), 68Q32, 68T05 (Secondary) G.1.9 The present paper is focused on the problem of recovering the Radon-Nikodym derivative under the big data assumption. To address the above problem, we design an algorithm that is a combination of the Nyström subsampling and the standard Tikhonov regularization. The convergence rate of the corresponding algorithm is established both in the case when the Radon-Nikodym derivative belongs to RKHS and in the case when it does not. We prove that the proposed approach not only ensures the order of accuracy as algorithms based on the whole sample size, but also allows to achieve subquadratic computational costs in the number of observations. |
| title | On recovering the Radon-Nikodym derivative under the big data assumption |
| topic | Numerical Analysis 65J20, 65R30 (Primary), 68Q32, 68T05 (Secondary) G.1.9 |
| url | https://arxiv.org/abs/2506.03891 |