[Compstats] Seminar tomorrow @ 4:30pm MC2018B: Ohad Shamir

Pascal Poupart ppoupart at cs.uwaterloo.ca
Tue Mar 23 16:13:27 EDT 2010


Tomorrow's talk will be given by Ohad Shamir who is visiting us from 
Israel.  Note the unusual room and time: *MC2018B @ 4:30pm*.

cheers, Pascal

Title: When Quantity makes Quality: Learning with Information Constraints

Speaker: Ohad Shamir
Date: Wednesday March 24
Time: 4:30pm
Location: MC2018B

In standard learning models, it is assumed that the learner has a 
complete and fully available training set at hand. However, in many 
real-world applications, obtaining full information on the training 
examples is expensive, illegal, or downright impossible. In this talk, I 
will discuss some new methods to learn in such information-constrained 
settings. These range from learning with only a few available features 
from each example; through coping with extremely noisy access to the 
data; to privacy-preserving learning. The underlying theme is that by 
gathering less information on more examples, one can be provably 
competitive with learning mechanisms which enjoy full access to the 
data. Along the way, I'll describe some novel techniques which might be 
of interest in their own right.

The talk is based on some recent joint works with Nicolò Cesa-Bianchi 
and Shai Shalev-Shwartz.

Pascal Poupart
Associate Professor
David R. Cheriton School of Computer Science
University of Waterloo
200 University Avenue West
Waterloo, Ontario
Canada N2L 3G1
Web: http://www.cs.uwaterloo.ca/~ppoupart
Email: ppoupart at cs.uwaterloo.ca 
Telephone: 1-519-888-4567x36239 
Fax: 1-519-885-1208

More information about the Compstats mailing list