[Colloquium] Reminder: TTI-C Show and Tell (Sham Kakade) 10.25.05 @12:15pm
Katherine Cumming
kcumming at tti-c.org
Fri Oct 21 14:55:42 CDT 2005
TTI-C SHOW AND TELL SERIES
Presented by: Toyota Technological Institute at Chicago
Speaker: Sham Kakade, TTI-C
Speaker's home page: http://www.tti-c.org//kakade.html
Time: Tuesday, October 25th, 2005
Location: TTI-C Conference Room
Lunch Provided @ 12:00pm
Seminar @ 12:15pm
Title: Worst Case Bounds for (Parametric and Non-Parametric) Bayesian
Algorithms
Abstract:
We present a competitive analysis of some non-parametric Bayesian algorithms
in a worst-case online learning setting, where no probabilistic assumptions
about the generation of the data are made. We consider models which use a
Gaussian process prior (over the space of all functions) and provide bounds
on the regret (under the log loss) for commonly used non-parametric Bayesian
algorithms --- including Gaussian regression and logistic regression ---
which show how these algorithms can perform favorably under rather general
conditions. These bounds explicitly handle the infinite dimensionality of
these non-parametric classes in a natural way. We also make formal
connections to the minimax and minimum description length (MDL) framework.
Here, we show precisely how Bayesian Gaussian regression is a minimax
strategy.
Joint work with: Dean Foster, Andrew Ng, Matthias Seeger
-----------------
If you have questions, or would like to meet the speaker, please contact
Katherine at 773-834-1994 or kcumming at tti-c.org. For information on future
TTI-C talks or events, please go to the TTI-C Events page,
http://www.tti-c.org/events.html. TTI-C (1427 East 60th Street, Chicago, IL
60637)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20051021/be2695c4/attachment.htm
More information about the Colloquium
mailing list