JSM 2014 Home
Online Program Home
My Program

Abstract Details

Activity Number: 409
Type: Contributed
Date/Time: Tuesday, August 5, 2014 : 2:00 PM to 2:45 PM
Sponsor: Section on Nonparametric Statistics
Abstract #314082
Title: Flexible Large Margin Classifiers: SVM, DWD, and Beyond
Author(s): Xingye Qiao*+ and Lingsong Zhang
Companies: SUNY Binghampton University and Purdue Univeristy
Keywords: classification ; high-dimensional, low-sample size ; Fisher consistency ; large margin classifier ; asymptotics
Abstract:

We provide a comprehensive study for large margin classifiers, focusing on their loss functions. In particular, two large margin classifiers, support vector machine and distance weighted discrimination, are thoroughly investigated. Motivated by the distinctive advantages and disadvantages of both methods in the presence of unbalanced sample size and high dimensionality, we provide two new proposals. The first proposed method is a unified machine bridging support vector machine and distance weighted discrimination, through a modified loss function. The second approach is a hybrid of both methods. It does not adopt a modification of the loss function. Instead, an axillary separating hyperplane is used to allow different modules which specifically tackle different issues in classification.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2014 program




2014 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Professional Development program, please contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

ASA Meetings Department  •  732 North Washington Street, Alexandria, VA 22314  •  (703) 684-1221  •  meetings@amstat.org
Copyright © American Statistical Association.