Decentralized Optimization with Mixed Affine Constraints

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yarmoshik, Demyan, Nguyen, Nhat Trung, Rogozin, Alexander, Gasnikov, Alexander
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915773892526080
author Yarmoshik, Demyan
Nguyen, Nhat Trung
Rogozin, Alexander
Gasnikov, Alexander
author_facet Yarmoshik, Demyan
Nguyen, Nhat Trung
Rogozin, Alexander
Gasnikov, Alexander
contents This paper considers decentralized optimization of convex functions with mixed affine equality constraints involving both local and global variables. Constraints on global variables may vary across different nodes in the network, while local variables are subject to coupled and node-specific constraints. Such problem formulations arise in machine learning applications, including federated learning and multi-task learning, as well as in resource allocation and distributed control. We analyze this problem under smooth and non-smooth assumptions, considering both strongly convex and general convex objective functions. Our main contribution is an optimal algorithm for the smooth, strongly convex regime, whose convergence rate matches established lower complexity bounds. We further provide near-optimal methods for the remaining cases.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04479
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Decentralized Optimization with Mixed Affine Constraints
Yarmoshik, Demyan
Nguyen, Nhat Trung
Rogozin, Alexander
Gasnikov, Alexander
Optimization and Control
This paper considers decentralized optimization of convex functions with mixed affine equality constraints involving both local and global variables. Constraints on global variables may vary across different nodes in the network, while local variables are subject to coupled and node-specific constraints. Such problem formulations arise in machine learning applications, including federated learning and multi-task learning, as well as in resource allocation and distributed control. We analyze this problem under smooth and non-smooth assumptions, considering both strongly convex and general convex objective functions. Our main contribution is an optimal algorithm for the smooth, strongly convex regime, whose convergence rate matches established lower complexity bounds. We further provide near-optimal methods for the remaining cases.
title Decentralized Optimization with Mixed Affine Constraints
topic Optimization and Control
url https://arxiv.org/abs/2602.04479