A Cyclic Coordinate Descent Algorithm for lq Regularization

Authors Jinshan Zeng, Zhimin Peng, Shaobo Lin, Zongben Xu

Publication date 3 August 2014

Abstract: In recent studies on sparse modeling,

l_{q}

(

0 < q < 1

) regularization has received considerable attention due to its superiorities on sparsity-inducing and bias reduction over the

l_{1}

regularization.In this paper, we propose a cyclic coordinate descent (CCD) algorithm for

l_{q}

regularization. Our main result states that the CCD algorithm converges globally to a stationary point as long as the stepsize is less than a positive constant. Furthermore, we demonstrate that the CCD algorithm converges to a local minimizer under certain additional conditions. Our numerical experiments demonstrate the efficiency of the CCD algorithm.

This page was built for publication: A Cyclic Coordinate Descent Algorithm for lq Regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6253659)