Sobolev Norm Learning Rates for Conditional Mean Embeddings
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2021
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918432660783104 |
|---|---|
| author | Talwai, Prem Shameli, Ali Simchi-Levi, David |
| author_facet | Talwai, Prem Shameli, Ali Simchi-Levi, David |
| contents | We develop novel learning rates for conditional mean embeddings by applying the theory of interpolation for reproducing kernel Hilbert spaces (RKHS). We derive explicit, adaptive convergence rates for the sample estimator under the misspecifed setting, where the target operator is not Hilbert-Schmidt or bounded with respect to the input/output RKHSs. We demonstrate that in certain parameter regimes, we can achieve uniform convergence rates in the output RKHS. We hope our analyses will allow the much broader application of conditional mean embeddings to more complex ML/RL settings involving infinite dimensional RKHSs and continuous state spaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2105_07446 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Sobolev Norm Learning Rates for Conditional Mean Embeddings Talwai, Prem Shameli, Ali Simchi-Levi, David Machine Learning Statistics Theory We develop novel learning rates for conditional mean embeddings by applying the theory of interpolation for reproducing kernel Hilbert spaces (RKHS). We derive explicit, adaptive convergence rates for the sample estimator under the misspecifed setting, where the target operator is not Hilbert-Schmidt or bounded with respect to the input/output RKHSs. We demonstrate that in certain parameter regimes, we can achieve uniform convergence rates in the output RKHS. We hope our analyses will allow the much broader application of conditional mean embeddings to more complex ML/RL settings involving infinite dimensional RKHSs and continuous state spaces. |
| title | Sobolev Norm Learning Rates for Conditional Mean Embeddings |
| topic | Machine Learning Statistics Theory |
| url | https://arxiv.org/abs/2105.07446 |