JSM 2005 - Toronto

Abstract #302826

This is the preliminary program for the 2005 Joint Statistical Meetings in Minneapolis, Minnesota. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2005); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.



The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

The Program has labeled the meeting rooms with "letters" preceding the name of the room, designating in which facility the room is located:

Minneapolis Convention Center = “MCC” Hilton Minneapolis Hotel = “H” Hyatt Regency Minneapolis = “HY”

Back to main JSM 2005 Program page
Legend: = Applied Session, = Theme Session, = Presenter
Activity Number: 9
Type: Invited
Date/Time: Sunday, August 7, 2005 : 2:00 PM to 3:50 PM
Sponsor: IMS
Abstract - #302826
Title: Information Theory and Risk Analysis for (nearly) Bayes Regression, Prediction, Density Estimation, and Machine Learning
Author(s): Andrew Barron*+
Companies: Yale University
Address: , New Haven, CT, 06520-8290,
Keywords:
Abstract:

Tools of information theory are presented for analysis of risk of statistical procedures. Fundamental roles bounding riskare played by indices of resolvability, which express the ideal balance between descriptive complexity (or log reciprocal prior probability) and model accuracy measured by relative entropy. Applications of the theory are discussed for model averaging of subset models in Gaussian regression, for minimum description length estimation in mixture density models, for relative entropy risk of predictive density estimators, for neural nets, and for adaptive kernel machines.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2005 program

JSM 2005 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2005