Thursday, January 25, 2007
4:15 pm
B17 Upson Hall

Computer Science
Colloquium
Spring 2007

Avrim Blum
Carnegie Mellon University
 

Thoughts on learning and clustering


In this talk I will present some thoughts on a few basic issues and recent trends in machine learning.  I will then describe new work we have been doing to develop an intuitive theoretical framework for one of these recent trends, the use of kernel methods. Kernel methods have proven to be very powerful tools in machine learning, allowing simple learning algorithms to be used in situations where fairly complex decision surfaces are needed.  They also have an existing fairly well-developed theory.  However, there has been a large gap between the "theoretical story" and practical intuition surrounding kernel methods, which our framework aims to narrow.  An interesting feature of our proposed framework is that it can also be applied to clustering.  In particular, I will discuss how it can be used to provide a new approach to analyzing clustering problems and the types of information needed to solve them, and how we should perhaps expand our concept of what it means to cluster well.

Portions of this talk include work joint with Nina Balcan and Santosh Vempala.