[Colloquium] TTIC Colloquium: John Langford

[Liv Leader]

When:     *Tuesday, March 22 @ 11 a.m.*

Where:    *TTIC Conference Room #526*, 6045 S. Kenwood Ave, 5th Floor

Who:      *John Langford*

Title:       *Learning with Exploration*

The default successful paradigm of machine learning is supervised learning.
Here humans are hired (often through mechanical turk these days) to label
items, and then the labeled information is fed into a learning algorithm to
create a learned predictor.  A more natural, less expensive, and accurate
approach is observe what works in practice, and use this information to
learn a predictor.

For people familiar with the first approach, there are several failure modes
ranging from plain inconsistency to mere suboptimality.   A core basic issue
here is the need for exploration---because if a choice is not explored, we
can't optimize for it.  The need for exploration implies a need for using
exploration to evaluate learned solutions, to guide the optimization of
learned predictors, and the need to control the process of exploration so as
to accomplish it efficiently.

I will provide an overview of the problems which crop up in this area, and
how to solve them.  This includes new results on policy evaluation and
optimization, with the first ever optimization-based exploration control
algorithms for this setting.

Host:     Joseph Keshet, jkeshet at ttic.edu

-- 
Liv Leader
Faculty Services

Toyota Technological Institute
6045 S Kenwood Ave, #504
Chicago, IL 60637
Phone- (773) 834-2567
Fax-     (773) 834-9881
Email-  lleader at ttic.edu <jam at ttic.edu>
Web-   www.ttic.edu



-- 
Liv Leader
Faculty Services

Toyota Technological Institute
6045 S Kenwood Ave, #504
Chicago, IL 60637
Phone- (773) 834-2567
Fax-     (773) 834-9881
Email-  lleader at ttic.edu <jam at ttic.edu>
Web-   www.ttic.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20110321/9d59f0f6/attachment.htm