Online Program Home
My Program

Abstract Details

Activity Number: 432
Type: Contributed
Date/Time: Tuesday, August 2, 2016 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #321411 View Presentation
Title: Nonparametric Classification Using a Forest Dependency Structure
Author(s): Mary Frances Dorn* and Clifford Spiegelman and Amit Moscovich and Boaz Nadler
Companies: Texas A&M University and Texas A&M University and Weizmann Institute of Science and Weizmann Institute of Science
Keywords: classification ; graphical models ; forest distributions
Abstract:

We propose a new nonparametric approach for binary classification that exploits the modeling flexibility of sparse graphical models. We assume that each class can be represented by a family of undirected sparse graphical models, specifically a forest-structured distribution. Our procedure requires the nonparametric estimation of only one- and two-dimensional marginal densities to transform the data into a space where a linear classifier is optimal. Experiments with simulated and real data indicate that the proposed method is competitive with popular methods across a range of applications.


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

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association