University of Cambridge > Talks.cam > Applied and Computational Analysis > Learning in Dynamical Systems

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Learning in Dynamical Systems

Download to your calendar using vCal

If you have a question about this talk, please contact Georg Maierhofer .

Learning in dynamical systems is a fundamental challenge underlying modern sequence modeling. Despite extensive study, efficient algorithms with formal guarantees for general nonlinear systems have remained elusive. This talk presents a provably efficient framework for learning in any bounded and Lipschitz nonlinear dynamical system, establishing the first sublinear regret guarantees in a dimension-free setting. Our approach combines Koopman lifting, Luenberger observers, and, crucially, spectral filtering to show that a broad class of nonlinear dynamics are learnable. These insights motivate a new neural architecture, the Spectral Transform Unit (STU), which we will describe and present preliminary experiments on open benchmarks of language modelling and dynamical systems.

This talk is part of the Applied and Computational Analysis series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

GR03, English Faculty Building, 9 West Road, Sidgwick Site and online https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBdXVpOXFvdz09 hjb78's list Hicks & Mead Rooms, University Centre, Granta Place

Other talks

Shape modes of CP^1 vortices Geometry and Generalization: The case of Grokking Title and abstract tba Polar Oceans Seminar Talk Theophilus Richmond’s The First Crossing: The Transition from Slavery to Indentureship in the Caribbean and the Case of the Black Slave on the Hesperus Evolution: Inevitable or Remarkable?
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity