[Colloquium] Talk by Philippe Rigollet, Georgia Institute of Technology on March 7, 2008

[caseyk]

DEPARTMENT OF COMPUTER SCIENCE

UNIVERSITY OF CHICAGO

Date: Friday, March 7, 2008
Time: 2:30 p.m.
Place: Ryerson 251, 1100 E. 58th Street

--------------------------------------------------

Speaker:	Philippe Rigollet

From:		Georgia Institute of Technology

Web page:	http://www.math.gatech.edu/~rigollet/

Title: Stochastic Convex Optimization Using Mirror Averaging Algorithms

Abstract: Several statistical problems where the goal is to minimize  
an unknown convex risk function, can be formulated in the general  
framework of stochastic convex optimization. For example the problem  
of model selection and more generally of aggregation can be treated  
using the machinery of stochastic optimization in several frameworks  
including density estimation, regression and convex classification. We  
describe a family of general algorithms called "mirror averaging  
algorithms" that yield an estimator (or a classifier) which attains  
optimal rates of model selection in several interesting cases. The  
theoretical results are presented in the form of exact oracle  
inequalities similar to those employed in optimization theory. The  
practical performance of the algorithms is illustrated on several real  
and artificial examples and compared to standard estimators or  
classifiers.

----------------------------------------------

Host: Partha Niyogi