On the Convergence of the Iterative Shrinkage/Thresholding Algorithm With a Weakly Convex Penalty

2015/10/31 by Ilker Bayram · 2 citations
Mathematics · #math.OC

paper · pdf · doi:10.1109/tsp.2015.2502551

arxiv created 2015/11/12 · arxiv updated 2016/04/20

Abstract

We consider the iterative shrinkage/thresholding algorithm (ISTA) applied to a cost function composed of a data fidelity term and a penalty term. The penalty is non-convex but the concavity of the penalty is accounted for by the data fidelity term so that the overall cost function is convex. We provide a generalization of the convergence result for ISTA viewed as a forward-backward splitting algorithm. We also demonstrate experimentally that for the current setup, using large stepsizes in ISTA can accelerate convergence more than existing schemes proposed for the convex case, like TwIST or FISTA.

Cited by

• Variable Smoothing for Weakly Convex Problems with Non-Euclidean Directions
• A proximal subgradient method for nonconvex stochastic optimization under the Kurdyka-Łojasiewicz condition