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

  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

ℹ️ Information

Graphical Models for Bandit Problems

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.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Hoyle Lecture Theatre + online Munby Room, King’s College (and online) Seminar Room, Henry Wellcome Building & on Zoom -https://zoom.us/meeting/register/tJEkcuCtrTwoG9I1M856dIPOpwYUO3q4WdIv

Other talks

Title to be confirmed Gastroenterology and Acute Medicine Argentina 2005 Discussion II continued A flexible Monte Carlo quantitative bias analysis for unmeasured confounding Online Causal Inference Seminar
 

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