An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications
This work addresses a persistent problem in statistical learning for researchers dealing with dependent data, though it appears incremental as it builds on existing Bernstein inequalities.
The paper tackles the challenge of learning from non-independent and non-identically distributed data by introducing data-dependent Bernstein inequalities for vector-valued processes in Hilbert spaces, achieving novel risk bounds for covariance operator estimation and operator learning in dynamical systems.
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.