There is a sign-up schedule for this event that can be found at

http://www.cs.utexas.edu/department/webevent/utcs/events/cgi/list_event

s.cgi

Type of Talk: UTCS Colloquia /AI

Speaker/Affiliation: Csaba
Szepesvari/University of Alberta

Date/Time: Wednesday, November 10,
2010, 11:00 a.m.

Location: ACES 2.402

Host: Peter Stone

Ta

lk Title: "How to choose cakes (if you must?) -- advice from statistics"

Talk Abstract:
Every time you visit a new town you go to its best conf

ectionery. Which cake to choose? Needless to say cakes are made a little di

fferently in every town. Should you choose the familiar favorite of yours o

r should you try a new one so that you are not missing something very good?
How to choose if there are a very large number of cakes, maybe more than

days in your life? Or even infinite? Of course, this problem is an instanc

e of the classic multi-armed bandit problem.

Applications range from p

roject management, pricing products, through calibration of physical proc

esses, monitoring and control of wireless networks, to optimizing website
content. In this talk I will describe some recent results about when the s

pace of options is very large or even infinite with more or less structure.
I will outline several open problems with varying difficulty. The talk is

based on joint work with (in chronological order) Peter Auer, Ronald Ortne

r (Graz, Austria), Yasin Abbasi-Yadkori (UofA), Sarah Filippi, Olivier

Cappe, Aurilien Garivier (Telecom ParisTech, CNRS), and Pallavi Arora an

d Rong Zheng (University of Houston, TX).

Speaker Bio:
Csaba Szepes

vari received his PhD in 1999 from University, Szeged, Hungary. He is cur

rently an Associate Professor at the Department of Computing Science of the
University of Alberta and a principal investigator of the Alberta Ingenuit

y Center for Machine Learning. Previously, he held a senior researcher pos

ition at the Computer and Automation Research Institute of the Hungarian Ac

ademy of Sciences, where he headed the Machine Learning Group. Before that

, he spent 5 years in the software industry. In 1998, he became the Resea

rch Director of Mindmaker, Ltd., working on natural language processing a

nd speech products, while from 2000, he became the Vice President of Rese

arch at the Silicon Valley company Mindmaker Inc. He is the coauthor of a b

ook on nonlinear approximate adaptive controllers, a recent short book on

Reinforcement Learning, published over 100 journal and conference papers.

He serves as the Associate Editor of IEEE Transactions on Adaptive Control

and AI Communications, is on the board of editors of the Journal of Machin

e Learning Research and the Machine Learning Journal, and is a regular mem

ber of the program committee at various machine learning and AI conferences

. His areas of expertise include statistical learning theory, reinforcemen

t learning and nonlinear adaptive control.