Open Access
Translator Disclaimer
March 2011 Coordinate descent algorithms for nonconvex penalized regression, with applications to biological feature selection
Patrick Breheny, Jian Huang
Ann. Appl. Stat. 5(1): 232-253 (March 2011). DOI: 10.1214/10-AOAS388

Abstract

A number of variable selection methods have been proposed involving nonconvex penalty functions. These methods, which include the smoothly clipped absolute deviation (SCAD) penalty and the minimax concave penalty (MCP), have been demonstrated to have attractive theoretical properties, but model fitting is not a straightforward task, and the resulting solutions may be unstable. Here, we demonstrate the potential of coordinate descent algorithms for fitting these models, establishing theoretical convergence properties and demonstrating that they are significantly faster than competing approaches. In addition, we demonstrate the utility of convexity diagnostics to determine regions of the parameter space in which the objective function is locally convex, even though the penalty is not. Our simulation study and data examples indicate that nonconvex penalties like MCP and SCAD are worthwhile alternatives to the lasso in many applications. In particular, our numerical results suggest that MCP is the preferred approach among the three methods.

Citation

Download Citation

Patrick Breheny. Jian Huang. "Coordinate descent algorithms for nonconvex penalized regression, with applications to biological feature selection." Ann. Appl. Stat. 5 (1) 232 - 253, March 2011. https://doi.org/10.1214/10-AOAS388

Information

Published: March 2011
First available in Project Euclid: 21 March 2011

zbMATH: 1220.62095
MathSciNet: MR2810396
Digital Object Identifier: 10.1214/10-AOAS388

Keywords: Coordinate descent , Lasso , MCP , optimization , penalized regression , SCAD

Rights: Copyright © 2011 Institute of Mathematical Statistics

JOURNAL ARTICLE
22 PAGES


SHARE
Vol.5 • No. 1 • March 2011
Back to Top