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:
|
509
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 1, 2012 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistical Learning and Data Mining
|
Abstract - #305423 |
Title:
|
Regularization Parameter Selection in Convex and Non-Convex Penalized Least Squares Estimation
|
Author(s):
|
Kei Hirose*+ and Shohei Tateishi and Sadanori Konishi
|
Companies:
|
Osaka University and Toyama Chemical Co., Ltd. and Chuo University
|
Address:
|
1-3, Machikaneyama-Cho, Toyonaka,, Osaka 560-8531, , Japan
|
Keywords:
|
Convex and non-convex penalties ;
Degrees of freedom ;
Model selection criteria ;
Model complexity
|
Abstract:
|
Sparse regression modeling via regularization such as the lasso has received much attention as a powerful tool for analyzing high-dimensional data. Crucial issues in the modeling process are the choice of tuning parameters including regularization parameters, which control the model complexity. The appropriate choice of tuning parameters can be viewed as a model selection and evaluation problem. Mallows' Cp type criteria may be used as a selection tool in lasso type regularization methods, for which the concept of degrees of freedom plays a key role. We introduce an efficient algorithm that computes the degrees of freedom by extending the generalized path seeking algorithm. Our procedure allows us to construct model selection criteria for evaluating models estimated by regularization with a wide variety of convex and non-convex penalties. The proposed method can be also applied to the problem of group variable selection such as the group lasso. We use Monte Carlo experiments and real data examples to investigate the properties of our modeling strategy.
|
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.