[Colloquium] Sindhwani/Dissertation Defense/8-3-07
Margaret Jaffey
margaret at cs.uchicago.edu
Fri Jul 20 11:07:56 CDT 2007
Department of Computer Science/The University of Chicago
*** Dissertation Defense ***
Candidate: Vikas Sindhwani
Date: Friday, August 3, 2007
Time and Location: 2:30 p.m. (tentative time) in Ryerson 276
Title: On Semi-supervised Kernel Methods
Abstract:
In many applications of machine learning, abundant amounts of data
can be cheaply and automatically collected. However, manual labeling
for the purposes of training learning algorithms is often a slow,
expensive, and error-prone process. The goal of semi-supervised
learning is to utilize a large collection of unlabeled data jointly
with a few labeled examples for improving generalization performance
(e.g., in classification, regression tasks). In this thesis, we
present families of algorithms: Manifold Regularization, Low-density
Methods and Co-regularization, for extending kernel methods (such as
Support Vector Machines) for Semi-supervised learning. These
algorithms are based on different operating assumptions on the
structure and geometry of the probability distribution underlying the
data. Empirical results on a variety of learning tasks, including
large-scale text categorization, confirm that this body of algorithms
obtain state-of-the-art performance.
Candidate's Advisor: Prof. Partha Niyogi
A draft copy of Mr. Sindhwani's dissertation will be available soon
in Ry 156.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Margaret P. Jaffey margaret at cs.uchicago.edu
Department of Computer Science
Student Support Rep (Ry 161A) (773) 702-6011
The University of Chicago http://www.cs.uchicago.edu
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
More information about the Colloquium
mailing list