|
Activity Number:
|
98
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Physical and Engineering Sciences
|
| Abstract - #308393 |
|
Title:
|
Evidence Contrary to the Statistical View of Boosting
|
|
Author(s):
|
David Mease*+
|
|
Companies:
|
San Jose State University
|
|
Address:
|
Department of Marketing and Decision Sci, San Jose, CA, 95192-0069,
|
|
Keywords:
|
AdaBoost ; Boosting Algorithms ; LogitBoost
|
|
Abstract:
|
The statistical perspective on boosting algorithms focuses on optimization, drawing parallels with maximum likelihood estimation for logistic regression. In this talk we present empirical evidence that raises questions about this view. Although the statistical perspective provides a theoretical framework within which it is possible to derive theorems and create new algorithms for general contexts, we show that there remain many unanswered important questions. Furthermore, we provide examples that reveal crucial flaws in the many practical suggestions and new algorithms that are derived from the statistical view. We examine experiments using simple simulation models to illustrate some of these flaws and their practical consequences. This is joint work with Abraham Wyner at the University of Pennsylvania.
|
