An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications

Erfan Mirzaei, Andreas Maurer, Vladimir R Kostic, Massimiliano Pontil

TL;DR: We developed empirical Bernstein inequalities and demonstrated how they can improve covariance estimation and enhance statistical guarantees for transfer operators.

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.

Submission Number: 2065