January 27, 2009: Seminar: Avrim Blum: "A Computational Theory of Clustering"

The University of Illinois at Chicago

Department of Computer Science

2008-2009 Distinguished Lecturer Seminar Series

A Computational Theory of Clustering

Avrim Blum
Carnegie Mellon University
Friday, February 6, 2009
1:00 p.m., Room 636 SEO


Problems of clustering data arise in many different areas. However, the question of which algorithm is best to use under what conditions remains poorly understood. The field of Machine Learning has benefited from a well-developed theory that allows one to analyze different machine learning algorithms and understand what information about a given task is needed in order for these algorithms to succeed. In this talk, I will describe work we have been doing on extending this theory to the problem of clustering. This work is based on a new way of understanding a class of techniques in machine learning known as kernel methods, and provides a new approach for analyzing clustering problems and the types of information needed to solve them. It also suggests how we should perhaps expand our concept of what it means to cluster well.

Brief Bio:

Avrim Blum is Professor of Computer Science at Carnegie Mellon University. His main research interests include Machine Learning Theory, Approximation Algorithms, and Algorithmic Game Theory, and he is also known for his work in AI Planning. He has served as Program Chair for the IEEE Symposium on Foundations of Computer Science (FOCS) and the Conference on Learning Theory (COLT), and on the organizing committee for the National Academy of Sciences U.S. Frontiers of Science Symposium. He was recepient of the Sloan Fellowship and NSF National Young Investigator Awards, and is a Fellow of the ACM.

Host: Professor Robert H. Sloan

Copyright 2016 The Board of Trustees
of the University of Illinois.webmaster@cs.uic.edu
Helping Women Faculty Advance
Funded by NSF