Iteration-Complexity of a Generalized Forward Backward Splitting Algorithm

MaRDI QIDQ6245890zbMATH OpenFDO

Authors Jingwei Liang, Jalal Fadili, Gabriel Peyré

Publication date 24 October 2013

Abstract: In this paper, we analyze the iteration-complexity of Generalized Forward--Backward (GFB) splitting algorithm, as proposed in cite{gfb2011}, for minimizing a large class of composite objectives $f+su{m}_{i=1}^n{h}_i$ on a Hilbert space, where $f$ has a Lipschitz-continuous gradient and the $h_i$'s are simple (ie their proximity operators are easy to compute). We derive iteration-complexity bounds (pointwise and ergodic) for the inexact version of GFB to obtain an approximate solution based on an easily verifiable termination criterion. Along the way, we prove complexity bounds for relaxed and inexact fixed point iterations built from composition of nonexpansive averaged operators. These results apply more generally to GFB when used to find a zero of a sum of $n>0$ maximal monotone operators and a co-coercive operator on a Hilbert space. The theoretical findings are exemplified with experiments on video processing.

This page was built for publication: Iteration-Complexity of a Generalized Forward Backward Splitting Algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6245890)