Please use this identifier to cite or link to this item:
Title: A Forward and Backward Stagewise algorithm for nonconvex loss functions with adaptive Lasso
Authors: Shi, XJ
Huang, Y
Huang, J 
Ma, SG
Keywords: Forward and Backward Stagewise
Nonconvex loss
Adaptive Lasso
Issue Date: 2018
Publisher: North-Holland
Source: Computational statistics and data analysis, Aug. 2018, v. 124, p. 235-251 How to cite?
Journal: Computational statistics and data analysis 
Abstract: Penalization is a popular tool for multi- and high-dimensional data. Most of the existing computational algorithms have been developed for convex loss functions. Nonconvex loss functions can sometimes generate more robust results and have important applications. Motivated by the BLasso algorithm, this study develops the Forward and Backward Stagewise (Fabs) algorithm for nonconvex loss functions with the adaptive Lasso (aLasso) penalty. It is shown that each point along the Fabs paths is a delta-approximate solution to the aLasso problem and the Fabs paths converge to the stationary points of the aLasso problem when delta goes to zero, given that the loss function has second-order derivatives bounded from above. This study exemplifies the Fabs with an application to the penalized smooth partial rank (SPR) estimation, for which there is still a lack of effective algorithm. Extensive numerical studies are conducted to demonstrate the benefit of penalized SPR estimation using Fabs, especially under high-dimensional settings. Application to the smoothed 0-1 loss in binary classification is introduced to demonstrate its capability to work with other differentiable nonconvex loss function.
EISSN: 0167-9473
DOI: 10.1016/j.csda.2018.03.006
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

Citations as of Dec 10, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.