Subgradient averaging for multi-agent optimisation with different constraint sets

TL;DR

This paper introduces a novel subgradient averaging algorithm for multi-agent optimization that handles non-differentiable objectives and different constraint sets per agent, ensuring convergence over time-varying networks.

Contribution

The paper extends distributed subgradient methods to accommodate agents with different constraints and provides convergence analysis for the proposed algorithm.

Findings

Algorithm converges asymptotically with step size η/(k+1).

Achieves a convergence rate of O(ln k / √k) in objective value.

Demonstrates effectiveness on robust and L2 regression problems.

Abstract

We consider a multi-agent setting with agents exchanging information over a possibly time-varying network, aiming at minimising a separable objective function subject to constraints. To achieve this objective we propose a novel subgradient averaging algorithm that allows for non-differentiable objective functions and different constraint sets per agent. Allowing different constraints per agent simultaneously with a time-varying communication network constitutes a distinctive feature of our approach, extending existing results on distributed subgradient methods. To highlight the necessity of dealing with a different constraint set within a distributed optimisation context, we analyse a problem instance where an existing algorithm does not exhibit a convergent behaviour if adapted to account for different constraint sets. For our proposed iterative scheme we show asymptotic convergence of the iterates to a minimum of the underlying optimisation problem for step sizes of the form $ \frac{\eta}{k+1} $, $ \eta > 0 $. We also analyse this scheme under a step size choice of $ \frac{\eta}{\sqrt{k+1}} $, $ \eta > 0 $, and establish a convergence rate of $ \mathcal{O}(\frac{\ln k}{\sqrt{k}}) $ in objective value. To demonstrate the efficacy of the proposed method, we investigate a robust regression problem and an $ \ell_2 $ regression problem with regularisation.