Probability Estimation for Large Margin Classifiers

• Activity Number: 526
• Type: Invited
• Date/Time: Thursday, August 2, 2007 : 10:30 AM to 12:20 PM
• Sponsor: ASA Interest Group on Statistical Learning and Data Mining
• Author(s): Junhui Wang*+ and Xiaotong Shen and Yufeng Liu
• Companies: Columbia University and The University of Minnesota and The University of North Carolina at Chapel Hill
• Keywords: Function estimation ; High dimension and low sample size ; Interval estimation ; Tuning ; Weighting

Abstract

Large margin classifiers have proven to be effective in delivering high predictive accuracy, particularly those focusing on the decision boundaries and bypassing the requirement of estimating the class probability given input for discrimination. As a result, these classifiers may not directly yield an estimated class probability, which is of interest itself. In this talk, I will present a novel method to estimate the class probability through sequential weighted classifications, by utilizing features of interval estimation of large margin classifiers. In particular, I will discuss four aspects: (1) the idea and methodology development; (2) tuning parameter selection; (3) regularization solution path; (4) a statistical learning theory. Numerical examples will be provided to demonstrate the advantage of our proposed methodology.