Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2507.07826 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916837277564928 |
|---|---|
| author | Mirzaei, Erfan Maurer, Andreas Kostic, Vladimir R. Pontil, Massimiliano |
| author_facet | Mirzaei, Erfan Maurer, Andreas Kostic, Vladimir R. Pontil, Massimiliano |
| contents | Learning from non-independent and non-identically distributed data poses a persistent challenge in statistical learning. In this study, we introduce data-dependent Bernstein inequalities tailored for vector-valued processes in Hilbert space. Our inequalities apply to both stationary and non-stationary processes and exploit the potential rapid decay of correlations between temporally separated variables to improve estimation. We demonstrate the utility of these bounds by applying them to covariance operator estimation in the Hilbert-Schmidt norm and to operator learning in dynamical systems, achieving novel risk bounds. Finally, we perform numerical experiments to illustrate the practical implications of these bounds in both contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07826 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications Mirzaei, Erfan Maurer, Andreas Kostic, Vladimir R. Pontil, Massimiliano Machine Learning Learning from non-independent and non-identically distributed data poses a persistent challenge in statistical learning. In this study, we introduce data-dependent Bernstein inequalities tailored for vector-valued processes in Hilbert space. Our inequalities apply to both stationary and non-stationary processes and exploit the potential rapid decay of correlations between temporally separated variables to improve estimation. We demonstrate the utility of these bounds by applying them to covariance operator estimation in the Hilbert-Schmidt norm and to operator learning in dynamical systems, achieving novel risk bounds. Finally, we perform numerical experiments to illustrate the practical implications of these bounds in both contexts. |
| title | An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.07826 |