Iteration-Complexity of a Generalized Forward Backward Splitting Algorithm

TL;DR

This paper analyzes the iteration-complexity of the Generalized Forward-Backward splitting algorithm for composite optimization problems, providing bounds and convergence guarantees, with applications demonstrated in video processing.

Contribution

It offers new iteration-complexity bounds for the GFB algorithm, including inexact and relaxed versions, applicable to a broad class of problems involving monotone operators.

Findings

Derived pointwise and ergodic complexity bounds for GFB

Established complexity bounds for fixed point iterations of nonexpansive operators

Validated theoretical results with experiments on video processing

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 $f + \sum_{i=1}^n h_i$ 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.