Imperial College London


Faculty of Natural SciencesDepartment of Mathematics




+44 (0)20 7594 1424b.hamzi Website




654Huxley BuildingSouth Kensington Campus





My current research interests are the analysis of control and random dynamical systems in Reproducing Kernel Hilbert Spaces in view of developing data-based methods for the analysis and prediction of random dynamical systems and  control strategies for nonlinear systems on the basis of observed data (rather than a pre-described model). I am particularly interested in developing a qualitative theory for dynamical systems in reproducing kernel Hilbert spaces with applications to systems with critical transitions.

In general, my research interests lie at the intersection(s) of:

* Control Theory
* Deterministic Dynamical Systems
* Learning Theory/Machine Learning
* Random Dynamical Systems

with a particular emphasis on the following problems:




Lee J, De Brouwer E, Hamzi B, et al., 2023, Learning dynamical systems from data: A simple cross-validation perspective, Part III: Irregularly-sampled time series, Physica D-nonlinear Phenomena, Vol:443, ISSN:0167-2789

Dingle K, Kamal R, Hamzi B, 2023, A note on a priori forecasting and simplicity bias in time series, Physica A: Statistical Mechanics and Its Applications, Vol:609, ISSN:0378-4371, Pages:128339-128339

Haasdonk B, Hamzi B, Santin G, et al., 2021, Kernel methods for center manifold approximation and a weak data-based version of the Center Manifold Theorem, Physica D-nonlinear Phenomena, Vol:427, ISSN:0167-2789

Hamzi B, Owhadi H, 2021, Learning dynamical systems from data: A simple cross-validation perspective, part I: Parametric kernel flows, Physica D-nonlinear Phenomena, Vol:421, ISSN:0167-2789

More Publications