[Colloquium] TTIC Talk-Ronald DeVore 4/1/05 @ 3pm

[Katherine Cumming]

TOYOTA TECHNOLOGICAL INSTITUTE TALK
 
Speaker:  Ronald A. DeVore, University of South Carolina
Speaker's homepage:  http://www.math.sc.edu/~devore/
 
Time:  Friday, April 1st @ 3:00pm
Location:  TTI-C Conference Room 
 
 
Title: The Regression Problem in Supervised Learning
 

Abstract: 
 
We shall give an overview of the regression problem in supervised
learning.  Our goal is to understand what is the best that we can expect
from learning algorithms in terms of accuracy performance in either
expectation or probability.  We shall draw a contrast between (i) prior
dependent algorithms where an assumption on the prior is used in  the
algorithm; and (ii) universal algorithms (called model selection in
statistics) in which no knowledge of a prior is assumed in the algorithm
itself. Of course, the evaluation of the performance of the algorithm
can only be made under some prior conditions.  We shall consider such
algorithm evaluation under priors described by either smoothness of the
regression function or by some assumption on its approximability.  This
presentation will provide an overview of the collaborative research of
the speaker with Gerard Kerkyacharian, Dominique Picard, and Vladimir
Temlyakov.  It is also a launching point for the construction of
numerically friendly adaptive algorithms for learning recently
constructed by the speaker and Peter Binev, Albert Cohen, Wolfgang
Dahmen, and Vladimir Temlyakov.


-----------------------------------------------------------------
 
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 and 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/20050325/7e03a5fa/attachment.htm