Salvato in:
Dettagli Bibliografici
Autori principali: Du, Xu, Zhou, Xiaohua, Zhu, Shijie
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.20716
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912315677343744
author Du, Xu
Zhou, Xiaohua
Zhu, Shijie
author_facet Du, Xu
Zhou, Xiaohua
Zhu, Shijie
contents The Augmented Lagrangian Alternating Direction Inexact Newton (ALADIN) method is a cutting-edge distributed optimization algorithm known for its superior numerical performance. It relies on each agent transmitting information to a central coordinator for data exchange. However, in practical network optimization and federated learning, unreliable information transmission often leads to packet loss, posing challenges for the convergence analysis of ALADIN. To address this issue, this paper proposes Flexible ALADIN, a random polling variant of ALADIN, and presents a rigorous convergence analysis, including global convergence for convex problems and local convergence for non-convex problems.
format Preprint
id arxiv_https___arxiv_org_abs_2503_20716
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Convergence Theory of Flexible ALADIN for Distributed Optimization
Du, Xu
Zhou, Xiaohua
Zhu, Shijie
Systems and Control
The Augmented Lagrangian Alternating Direction Inexact Newton (ALADIN) method is a cutting-edge distributed optimization algorithm known for its superior numerical performance. It relies on each agent transmitting information to a central coordinator for data exchange. However, in practical network optimization and federated learning, unreliable information transmission often leads to packet loss, posing challenges for the convergence analysis of ALADIN. To address this issue, this paper proposes Flexible ALADIN, a random polling variant of ALADIN, and presents a rigorous convergence analysis, including global convergence for convex problems and local convergence for non-convex problems.
title Convergence Theory of Flexible ALADIN for Distributed Optimization
topic Systems and Control
url https://arxiv.org/abs/2503.20716