University of Cambridge > Talks.cam > Machine Learning @ CUED > Nonlinear Dynamics of Learning

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

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

ℹī¸ Information

Nonlinear Dynamics of Learning

Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani .

We describe a class of deterministic weakly chaotic dynamical systems with infinite memory. These ``herding systems’’ combine learning and inference into one algorithm. They convert moments directly into a sequence of pseudo-samples without learning an explicit model. Using the “perceptron cycling theorem” we can show that Monte Carlo estimates based on these pseudo-samples converge at an optimal rate of O(1/T), due to infinite range negative auto-correlations. We show that the information content of these sequences, as measured by sub-extensive entropy, can grow as fast as K*log(N). In continuous spaces we can control an infinite number of moments by formulating herding in a Hilbert space. Also in this case sample averages over arbitrary functions in the Hilbert space will converge at an optimal rate of O(1/T). More generally, we advocate the application of the rich theoretical framework of nonlinear dynamical systems and chaos theory to statistical learning.

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Rayleigh Seminar Room, Maxwell Centre, Cavendish Laboratory Richard Room, Darwin College Webinar & FW11, Computer Laboratory, William Gates Building.

Other talks

Cambridge AI in Medicine Seminar - July 2026 Title to be confirmed John Kendrew Lecture - Title TBC Disentangling preventative & ejective AGN feedback on a population basis with simulations, observations & machine learning Title TBC Group Presentation 1
 

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