Distributed optimization requires nodes to coordinate, yet full synchronization scales poorly. When n nodes collaborate through m pairwise regularizers, standard methods demand O(m) communications per iteration. This paper proposes randomized local coordination: each node independently samples one regularizer uniformly and coordinates only with nodes sharing that term. This exploits partial separability, where each regularizer Gj depends on a subset Sj⊆{1,…,n} of nodes. For graph-guided regularizers where ∣Sj∣=2, expected communication drops to exactly 2 messages per iteration. This method achieves O~(ε−2) iterations for convex objectives and under strong convexity, O(ε−1) to an ε-solution and O(log(1/ε)) to a neighborhood. Replacing the proximal map of the sum ∑jGj with the proximal map of a single randomly selected regularizer Gj preserves convergence while eliminating global coordination. Experiments validate both convergence rates and communication efficiency across synthetic and real-world datasets.
@article{arxiv.2509.14488,
title = {Decentralized Optimization with Topology-Independent Communication},
author = {Ying Lin and Yao Kuang and Ahmet Alacaoglu and Michael P. Friedlander},
journal= {arXiv preprint arXiv:2509.14488},
year = {2025}
}