[Colloquium] Reminder: TTI-C Talks TODAY; ML Summer School/Learning Theory Program

[Katherine Cumming]

Machine Learning Summer School-Applied Lecture
Speaker:  Cristian Sminchisescu, TTI-C
Speaker's homepage: http://www.tti-c.org//sminchisescu.html
<http://www.tti-c.org/sminchisescu.html> 
Time:  Thursday, May 19th at 2:00pm
Location:  TTI-C
Title:  Human Analysis in Video
Abstract:
Space is limited. For more information on this session for Machine
Learning Summer School participants
<http://chicago05.mlss.cc/tiki/tiki-read_article.php?articleId=7> Click
Here.
 
Machine Learning Summer School
Speaker:  Mauro Maggioni, Yale University
Speaker's homepage: http://www.math.yale.edu/~mmm82/
Time:  Thursday, May 19th at 2:00pm
Location:  International House-University of Chicago
 Title: TBA
Abstract: TBA
 
Machine Learning Summer School/Learning Theory Program 
Speaker:  Andrea Caponetto, University of Genoa
Speaker's homepage:
http://www.pascal-network.org/Network/Researchers/150/
Time:  Thursday, May 19th at 3:00pm
Location:  International House-University of Chicago        
Title: Optimal Rates for Regularized Least-Squares Algirithm in
Semi-Supervised Regression
Abstract: TBA
 
Machine Learning Summer School/Learning Theory Program 
Speaker:  Petra Phillips, Australia National University
Speaker's homepage:
http://www.anu.edu.au/RSISE/teleng/teleng2004/people/students/petra.php
Time:  Thursday, May 19th at 4:30pm
Location:  International House-University of Chicago        
Title: Data-Dependent Local Complexities for ERM
Abstract: 
We present data-dependent generalization bounds for a specific algorithm
which is of central importance in learning theory, namely the Empirical
Risk Minimization algorithm (ERM).

New results in Bartlett and Mendelson (2005) show that one can
significantly improve the estimates for the convergence rates for
empirical minimizers by a direct analysis of the ERM algorithm in the
case when the loss class satisfies certain structural assumptions. These
results are based on a local notion of complexity of subsets of
hypothesis functions with identical expected errors. We investigate the
extent to which one can estimate these convergence rates in a
data-dependent manner. We provide an algorithm which computes a
data-dependent upper bound for the expected error of empirical
minimizers in terms of the complexity of data-dependent local subsets.
These subsets are sets of functions of empirical errors of a given range
and can be determined based solely on empirical data. We then show that
the direct estimate in Bartlett and Mendelson (2005), which is an
essentially sharp estimate on the convergence rate for the ERM
algorithm, can not be recovered universally from empirical data. 
 
-----------------------------------------------------------------
If you have questions, or would like to meet the speaker, please contact
Katherine at 773-834-1994 or  <mailto:kcumming at tti-c.org>
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>
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/20050519/386c2294/attachment.htm