Abstract Details
|
Activity Number:
|
251
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2014 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistical Learning and Data Mining
|
|
Abstract #313315
|
|
|
Title:
|
Smooth Positive-Definite L1-Penalized Estimation of Large Cross-Spectrum Matrices
|
|
Author(s):
|
Yuan Qu*+
|
|
Companies:
|
Texas A&M
|
|
Keywords:
|
Smoothness ;
Positive-definite estimation ;
Sparsity ;
Cross-spectral estimation ;
Alternating direction methods ;
Soft-thresholding
|
|
Abstract:
|
In the spectral analysis, it is essential to estimate the cross-spectral matrix, which is complex-valued, positive definite and continuous with respect to the frequency. In this work, we employ the ideas of L_1 regularization and roughness penalization, and propose a new approach to estimate the sparse large cross spectrum matrix. We develop an alternating direction method to solve the challenging optimization problem and prove its convergence properties. Both simulation and real applications also demonstrate the competitive finite-sample performance of our proposal.
|
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.
Copyright © American Statistical Association.