Optimality in Decentralized Optimization under Bandwidth Constraints

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Tyurin, Alexander
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911534219788288
author Tyurin, Alexander
author_facet Tyurin, Alexander
contents We consider a realistic decentralized setup with bandwidth-constrained communication and derive optimal time complexities for non-convex stochastic parallel and asynchronous optimization (up to logarithmic factors). We develop the corresponding methods, Grace SGD and Leon SGD, for both homogeneous and heterogeneous settings. Unlike previous work, our optimal bounds are characterized in terms of min-cut/max-flow quantities and rely on tools from Gomory-Hu trees and Steiner Tree Packing problems, providing tighter and more practical complexities.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20735
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Optimality in Decentralized Optimization under Bandwidth Constraints
Tyurin, Alexander
Optimization and Control
Distributed, Parallel, and Cluster Computing
Combinatorics
We consider a realistic decentralized setup with bandwidth-constrained communication and derive optimal time complexities for non-convex stochastic parallel and asynchronous optimization (up to logarithmic factors). We develop the corresponding methods, Grace SGD and Leon SGD, for both homogeneous and heterogeneous settings. Unlike previous work, our optimal bounds are characterized in terms of min-cut/max-flow quantities and rely on tools from Gomory-Hu trees and Steiner Tree Packing problems, providing tighter and more practical complexities.
title Optimality in Decentralized Optimization under Bandwidth Constraints
topic Optimization and Control
Distributed, Parallel, and Cluster Computing
Combinatorics
url https://arxiv.org/abs/2603.20735