The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
Activity Number:
|
466
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 1, 2012 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Statistical Learning and Data Mining
|
Abstract - #305427 |
Title:
|
The Sparse-MLE for Variable Screening in Ultra-High-Dimensional Feature Space
|
Author(s):
|
Chen Xu*+ and Jiahua Chen
|
Companies:
|
University of British Columbia and SSC
|
Address:
|
333-6356 Agricultural Road, Vancouver, BC, V6T 1Z2, Canada
|
Keywords:
|
Variable screening ;
Screening consistency ;
Sparse MLE ;
High dimensionality ;
Penalized likelihood ;
Hard thresholding
|
Abstract:
|
Variable selection and feature extraction are fundamental for knowledge discovery and statistical modeling with high-dimensionality. For the computational feasibility, reducing the dimension of data is a necessary step before the formal analysis. Fan and Lv (2008) suggested a variable screening strategy based on the marginal correlations between the covariates and the response. In the same spirit, we propose a new screening approach via the sparsity-restricted maximum likelihood estimator (sparse-MLE) to account for more joint effects among the covariates. The new approach efficiently screens out most irrelevant variables from the model while retains those important ones with high probability. The low-dimensional model produced by sparse-MLE then serves as a good starting point for the further selection. We establish the screening consistency of the sparse-MLE and further develop an efficient algorithm for its implementation. The excellent performances of proposed method are supported by extensive numerical studies.
|
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 2012 program
|
2012 JSM Online Program Home
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.