University of Cambridge > > Machine Learning @ CUED > Graphical Models for Bandit Problems

Graphical Models for Bandit Problems

Add to your list(s) Download to your calendar using vCal

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

We introduce a rich class of graphical models for multi-armed bandit problems that permit both the state or context space and the action space to be very large. Settings where the number of contexts and actions are both large are becoming common in applied settings such as sponsored search and quantitative trading. We then present an algorithm for such models whose regret is bounded by the number of parameters and whose running time depends only on the treewidth of the graph substructure induced by the action space.

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.


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