An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications
Abstract
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.
Cite
Text
Mirzaei et al. "An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.Markdown
[Mirzaei et al. "An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.](https://mlanthology.org/aistats/2025/mirzaei2025aistats-empirical/)BibTeX
@inproceedings{mirzaei2025aistats-empirical,
title = {{An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications}},
author = {Mirzaei, Erfan and Maurer, Andreas and Kostic, Vladimir R and Pontil, Massimiliano},
booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
year = {2025},
pages = {5158-5166},
volume = {258},
url = {https://mlanthology.org/aistats/2025/mirzaei2025aistats-empirical/}
}