A distributed proximal splitting method with linesearch for locally Lipschitz gradients

TL;DR

This paper introduces a distributed proximal splitting algorithm with linesearch for multi-agent optimization problems with locally Lipschitz continuous gradients, removing the need for global Lipschitz constants and predefined stepsizes.

Contribution

It presents a novel distributed primal-dual proximal-gradient method with backtracking linesearch that adapts stepsizes locally, suitable for problems lacking global Lipschitz constants.

Findings

Algorithm converges under local Lipschitz conditions.

Linesearch procedure adapts stepsizes effectively.

Applicable to min-max convex-concave problems.

Abstract

In this paper, we propose a distributed first-order algorithm with backtracking linesearch for solving multi-agent minimisation problems, where each agent handles a local objective involving nonsmooth and smooth components. Unlike existing methods that require global Lipschitz continuity and predefined stepsizes, our algorithm adjusts stepsizes using distributed linesearch procedures, making it suitable for problems where global constants are unavailable or difficult to compute. The proposed algorithm is designed within an abstract linesearch framework for a primal-dual proximal-gradient method to solve min-max convex-concave problems, enabling the consensus constraint to be decoupled from the optimisation task. Our theoretical analysis allows for gradients of functions to be locally Lipschitz continuous, relaxing the prevalent assumption of globally Lipschitz continuous gradients.