[Compstats] Google-UW ML seminar: Wed May 5th @ 4pm MC5158

Pascal Poupart ppoupart at cs.uwaterloo.ca
Fri Apr 30 10:33:47 EDT 2010

Hi everyone,

David McAllester (from the Toyota Technological Institute) will be our 
guest on May 5th and May 6th.  He will give the second Google-UW Machine 
Learning seminar next week on Wednesday @ 4pm in MC5158.  He is a world 
leader in Machine Learning.  I encourage everyone to attend.  We will 
also webcast his talk.  So, if you'd like to see his talk remotely, you 
can login (up to 30 minutes before the talk) by clicking on the link 
below to watch David McAllester in real time.  Title ans abstract follow 


Title: Frequents vs. Bayesians, the PAC-Bayesian synthesis, and support 
vector machines.
Speaker: David McAllester (Toyota Technological Institute)

Date: Wednesday May 5th
Time: 4pm
Location: MC5158
Webcast: http://powerlink.powerstream.net/003/02484/live1.asx
Seminar series website: http://compstats.uwaterloo.ca/google


We will start with a description of the frequentist (objective 
probability) and Bayesian (subjective probability) positions. We will 
then describe the PAC-Bayesian theorem which allows for a kind of formal 
synthesis of the two positions. The talk will then focus on support 
vector machines as a case study in PAC-Bayesian analysis. We will 
discuss the "SVM scandal" --- no meaningful formal justification for the 
hinge loss of soft SVMs has ever been given. We will also apply 
PAC-Bayesian analysis to recent trends in structural SVMs. Structural 
SVMs are a way of training the parameters of graphical models and are 
becoming increasingly popular in areas such as computer vision and 
natural language processing.


Professor McAllester received his B.S., M.S., and Ph.D. degrees from the 
Massachusetts Institute of Technology in 1978, 1979, and 1987 
respectively. He served on the faculty of Cornell University for the 
academic year of 1987-1988 and served on the faculty of MIT from 1988 to 
1995. He was a member of technical staff at AT&T Labs-Research from 1995 
to 2002. He has been a fellow of the American Association of Artificial 
Intelligence (AAAI) since 1997. Since 2002 he has been Chief Academic 
Officer at the Toyota Technological Institute at Chicago. He has 
authored over 90 refereed publications. Professor McAllester's research 
areas include machine learning, the theory of programming languages, 
automated reasoning, AI planning, computer game playing (computer 
chess), computational linguistics and computer vision. A 1991 paper on 
AI planning proved to be one of the most influential papers of the 
decade in that area. A 1993 paper on computer game algorithms influenced 
the design of the algorithms used in the Deep Blue system that defeated 
Gary Kasparov. A 1998 paper on machine learning theory introduced 
PAC-Bayesian theorems which combine Bayesian and nonBayesian methods. He 
is currently part of a team that has scored in the top two places in the 
PASCAL object detection challenge (computer vision) in 2007, 2008 and 2009.

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