ISyE Statistics Seminar: Dr. Philippe Rigollet

Event Details
  • Date/Time:
    • Friday February 2, 2007
      10:00 am - 11:00 am
  • Location: Instructional Center, Rm 105
  • Phone:
  • URL:
  • Email:
  • Fee(s):
    N/A
  • Extras:
Contact
Yajun Mei
ISyE
Contact Yajun Mei
404-894-2300
Summaries

Summary Sentence: ISyE Statistics Seminar: Dr. Philippe Rigollet

Full Summary: ISyE Statistics Seminar: Stochastic convex optimization using mirror averaging algorithms.

ISyE Statistics Seminar: Stochastic convex optimization using mirror averaging algorithms

GUEST LECTURER
Dr. Philippe Rigollet

AFFILIATION
School of Mathematics, Georgia Tech

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, density estimation, regression and convex classification can be treated using the machinery of stochastic optimization. We describe a family of general algorithms called "mirror averaging algorithms" that yields and estimator (or a classifier) which attains optimal rates of convergence in several interesting cases. These optimal rates are illustrated on several examples and compared to standard estimators or classifiers.

Additional Information

In Campus Calendar
No
Groups

H. Milton Stewart School of Industrial and Systems Engineering (ISYE)

Invited Audience
No audiences were selected.
Categories
Seminar/Lecture/Colloquium
Keywords
Dr. Philippe Rigollet, ISyE Statistics Seminar
Status
  • Created By: Ruth Gregory
  • Workflow Status: Published
  • Created On: Oct 12, 2009 - 5:22pm
  • Last Updated: Oct 7, 2016 - 9:48pm