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

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

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

Nonlinear Dynamics of Learning

Add to your list(s) 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.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Organismal Proteostasis: Molecular Strategies for Proteome Protection in Health and Disease Veterinary anaesthesia Meeting the Challenge of Healthy Ageing in the 21st Century

Other talks

A rose by any other name Deep supervised level set method: an approach to fully automated segmentation of cardiac MR images in patients with pulmonary hypertension 'Alas, poor Yorick!': Laurence Sterne's "A Sentimental Journey" after 250 years' Making Refuge: Calais and Cambridge Attentional episodes and cognitive control ADMM for Exploiting Structure in MPC Problems Migration in Science Graded linearisations for linear algebraic group actions Katie Field - Symbiotic options for the conquest of land Cambridge - Corporate Finance Theory Symposium September 2017 - Day 1 Replication or exploration? Sequential design for stochastic simulation experiments
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity