[Colloquium] Reminder: Guest Speakers @ TTI-C Today (3/3/06)

[Katherine Cumming]

**********TTI-C Guest Speakers  Today ***********
                           March 3, 2006
        Presented by:  Toyota Technological Institute at Chicago
 
 (1)
 
Speaker: Tong Zhang, Yahoo
Speaker's home page: http://www-cs-students.stanford.edu/~tzhang/
 
Date:  Friday, March 3, 2006 
Location: TTI-C Conference Room (Machine Learning  Seminar Guest)
Time:  12:00pm
Title:  Learning with Structured Inputs
Abstract:
I will present a novel approach to semi-supervised learning that employs a
method, which we refer to as structural learning (aka multi-task learning).

The idea is to learn predictive structures from many auxiliary problems that
are created from the unlabeled data (and are related to the target problem),
and then transfer the learned structure to the supervised target problem.
In the first part, I will give a high-level description of the general
approach, a specific bi-linear structure model we use, and then explain how
we generate auxiliary problems that are related to the target task.  I will
then show some empirical results.  For example, this method produces
performance higher than the previous best results on some standard NLP
benchmark tests.  It is also highly effective for some other problems such
as image classification and even information retrieval.  In particular, I
will describe our successful participation in 2005's TREC genomics ad hoc
retrieval task using this idea.

In the second part, I will present a general framework for learning
structures including its learning theoretical analysis.  Under this
framework, I will investigate the theoretical justification of the bi-linear
structure model used in our experiments, and show that the resulting
formulation can be solved by an iterative SVD procedure.  The relationship
of this framework and transfer learning, and Bayesian hierarchical models
will be discussed.
(2)
 
Speaker:  Bhaskar DasGupta, University of Illinois at Chicago
Speaker's home page: http://www.cs.uic.edu/~dasgupta/
 
Date: Friday, March 3, 2006 
Location: TTI-C Conference Room (Bioinformatics Seminar Guest)
Time:  3:00pm
Title:  Randomized Approximations for Offline and Online Set-multicover
Problems
 
Abstract:
 
In this talk, I will describe randomized approximation algorithms for
offline and (time permitting) online versions of set multicover problems
that improve the previously best known expected approximation ratio and
competitive ratio bounds as a function of the coverage factor.

As an illustration of its application to systems biology, I will show how
our algorithms can be used to design experiments of approximately optimal
costs for some seemingly unrelated reverse engineering problems of
biological networks.

Very minimal knowledge of biology or control theory will be assumed for this
talk.

(These are joint results with Piotr Berman and Eduardo Sontag)
 
----------------------------------------------------------------------------
------
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/20060303/9e1f71dd/attachment.htm