[Colloquium] Talks at TTIC: Shubhendu Trivedi, TTIC Student
Dawn Ellis
dellis at ttic.edu
Tue Aug 12 17:38:22 CDT 2014
When: Thursday, August 28th at 11am
Where: TTIC, 6045 S Kenwood Avenue, 5th Floor, Room #526
Speaker: Shubhendu Trivedi, TTIC-Student Talk
Title: "Discriminative Metric Learning by Neighborhood Gerrymandering"
Abstract:
We formulate the problem of metric learning for k nearest neighbor
classification
as a large margin structured prediction problem, with a latent variable
representing
the choice of neighbors and the task loss directly corresponding to
classification
error. We describe an efficient algorithm for exact loss augmented
inference, and
a fast gradient descent algorithm for learning in this model. The objective
drives
the metric to establish neighborhood boundaries that benefit the true class
labels
for the training points. Our approach, reminiscent of gerrymandering
(redrawing
of political boundaries to provide advantage to certain parties), is more
direct in
its handling of optimizing classification accuracy than those previously
proposed.
In experiments on a variety of data sets our method is shown to achieve
excellent
results compared to current state of the art in metric learning.
This is joint work with Gregory Shakhnarovich and David McAllester.
Advisor: Greg Shakhnarovich, greg at ttic.edu
--
*Dawn Ellis*
Administrative Coordinator,
Bookkeeper
773-834-1757
dellis at ttic.edu
TTIC
6045 S. Kenwood Ave.
Chicago, IL. 60637
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20140812/2b846050/attachment.htm
More information about the Colloquium
mailing list