Year: 2024
Type: article
Abstract: In decentralized optimization, nodes of a communication network each possess a local objective function, and communicate using gossip-based methods in order to minimize the average of these per-node functions. While synchronous algorithms are heavily impacted by a few slow nodes or edges in the graph (thestraggler problem), their asynchronous counterparts are notoriously harder to parameterize. Indeed, their convergence properties for networks with heterogeneous communication and computation delays have defied analysis so far. In this article, we use acontinuizedframework to analyze asynchronous algorithms in networks with delays. Our approach yields a precise characterization of convergence time and of its dependence on heterogeneous delays in the network. Our continuized framework benefits from the best of both continuous and discrete worlds: the algorithms it applies to are based on event-driven updates. They are thus essentially discrete, and hence, readily implementable. Yet their analysis is essentially in continuous time, relying in part on the theory of delayed ordinary differential equations. Our algorithms moreover achieve anasynchronous speedup:their rate of convergence is controlled by the eigengap of the network graph weighted by local delays instead of the network-wide worst-case delay as in previous analyses. Our methods thus enjoy improved robustness to stragglers.
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4402215723
