OCLGMLSep 14, 2020

Distributed Mirror Descent with Integral Feedback: Asymptotic Convergence Analysis of Continuous-time Dynamics

arXiv:2009.06747v17 citations
Originality Incremental advance
AI Analysis

This work addresses distributed optimization problems in multi-agent systems, offering an incremental improvement by incorporating integral feedback for constant step-size convergence.

The paper tackles distributed optimization for a network of agents minimizing a global strongly convex objective by proposing a continuous-time distributed mirror descent algorithm with integral feedback, which converges to the global optimum using purely local information and shows improved convergence rates in numerical experiments.

This work addresses distributed optimization, where a network of agents wants to minimize a global strongly convex objective function. The global function can be written as a sum of local convex functions, each of which is associated with an agent. We propose a continuous-time distributed mirror descent algorithm that uses purely local information to converge to the global optimum. Unlike previous work on distributed mirror descent, we incorporate an integral feedback in the update, allowing the algorithm to converge with a constant step-size when discretized. We establish the asymptotic convergence of the algorithm using Lyapunov stability analysis. We further illustrate numerical experiments that verify the advantage of adopting integral feedback for improving the convergence rate of distributed mirror descent.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes