Decentralized Online Optimization With Compressed Communication Over Directed Graphs

Honglei Liu; Baoyong Zhang; Zhan Yu; Deming Yuan; Mingcheng Dai

doi:10.1109/TNNLS.2025.3622106

Decentralized Online Optimization With Compressed Communication Over Directed Graphs

Honglei Liu
, Baoyong Zhang^*
, Zhan Yu^*
, Deming Yuan
, Mingcheng Dai

^*Corresponding author for this work

Department of Mathematics

Research output: Contribution to journal › Journal article › peer-review

1 Citation (Scopus)

Abstract

This article focuses on a decentralized online optimization problem over multiagent systems, where the interactions are modeled by a strongly connected directed graph. The objective of each agent is to minimize the global loss function accumulated by all agents’ local loss functions, which are time-varying and only known by themselves. To address the communication bottleneck caused by the high-dimensional data and large-scale networks, we design a decentralized online algorithm with compressed communication, decentralized online gradient push-sum with compressed communication (CC-DOGPS). For strongly convex functions, a sublinear regret bound O(InT ²) of our designed algorithm is obtained, where T is the time horizon. Finally, two numerical simulations are given to validate the theoretical results and illustrate the efficiency of our designed algorithm.

Original language	English
Pages (from-to)	1533-1545
Number of pages	13
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	37
Issue number	4
Early online date	28 Oct 2025
DOIs	https://doi.org/10.1109/TNNLS.2025.3622106
Publication status	Published - 1 Apr 2026

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

User-Defined Keywords

Compressed communication
decentralized online optimization
directed graph
push-sum

Access to Document

10.1109/TNNLS.2025.3622106

Cite this

@article{f8c091f153b341b7885c03266bd8f1f6,

title = "Decentralized Online Optimization With Compressed Communication Over Directed Graphs",

abstract = "This article focuses on a decentralized online optimization problem over multiagent systems, where the interactions are modeled by a strongly connected directed graph. The objective of each agent is to minimize the global loss function accumulated by all agents{\textquoteright} local loss functions, which are time-varying and only known by themselves. To address the communication bottleneck caused by the high-dimensional data and large-scale networks, we design a decentralized online algorithm with compressed communication, decentralized online gradient push-sum with compressed communication (CC-DOGPS). For strongly convex functions, a sublinear regret bound O(InT 2) of our designed algorithm is obtained, where T is the time horizon. Finally, two numerical simulations are given to validate the theoretical results and illustrate the efficiency of our designed algorithm.",

keywords = "Compressed communication, decentralized online optimization, directed graph, push-sum",

author = "Honglei Liu and Baoyong Zhang and Zhan Yu and Deming Yuan and Mingcheng Dai",

note = "This work was supported in part by the National Natural Science Foundation of China under Grant 62273181, Grant 62373190, Grant 62221004, and Grant 12401123; in part by the Research Grants Council of the Hong Kong Special Administrative Region, China, under Grant HKBU 12301424; and in part by the Open Projects of the Institute of Systems Science, Beijing Wuzi University, under Grant BWUISS20 Publisher Copyright: {\textcopyright} 2025 IEEE.",

year = "2026",

month = apr,

day = "1",

doi = "10.1109/TNNLS.2025.3622106",

language = "English",

volume = "37",

pages = "1533--1545",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-2388",

publisher = "IEEE Computational Intelligence Society",

number = "4",

}

TY - JOUR

T1 - Decentralized Online Optimization With Compressed Communication Over Directed Graphs

AU - Liu, Honglei

AU - Zhang, Baoyong

AU - Yu, Zhan

AU - Yuan, Deming

AU - Dai, Mingcheng

N1 - This work was supported in part by the National Natural Science Foundation of China under Grant 62273181, Grant 62373190, Grant 62221004, and Grant 12401123; in part by the Research Grants Council of the Hong Kong Special Administrative Region, China, under Grant HKBU 12301424; and in part by the Open Projects of the Institute of Systems Science, Beijing Wuzi University, under Grant BWUISS20 Publisher Copyright: © 2025 IEEE.

PY - 2026/4/1

Y1 - 2026/4/1

N2 - This article focuses on a decentralized online optimization problem over multiagent systems, where the interactions are modeled by a strongly connected directed graph. The objective of each agent is to minimize the global loss function accumulated by all agents’ local loss functions, which are time-varying and only known by themselves. To address the communication bottleneck caused by the high-dimensional data and large-scale networks, we design a decentralized online algorithm with compressed communication, decentralized online gradient push-sum with compressed communication (CC-DOGPS). For strongly convex functions, a sublinear regret bound O(InT 2) of our designed algorithm is obtained, where T is the time horizon. Finally, two numerical simulations are given to validate the theoretical results and illustrate the efficiency of our designed algorithm.

AB - This article focuses on a decentralized online optimization problem over multiagent systems, where the interactions are modeled by a strongly connected directed graph. The objective of each agent is to minimize the global loss function accumulated by all agents’ local loss functions, which are time-varying and only known by themselves. To address the communication bottleneck caused by the high-dimensional data and large-scale networks, we design a decentralized online algorithm with compressed communication, decentralized online gradient push-sum with compressed communication (CC-DOGPS). For strongly convex functions, a sublinear regret bound O(InT 2) of our designed algorithm is obtained, where T is the time horizon. Finally, two numerical simulations are given to validate the theoretical results and illustrate the efficiency of our designed algorithm.

KW - Compressed communication

KW - decentralized online optimization

KW - directed graph

KW - push-sum

UR - https://www.scopus.com/pages/publications/105020741257

U2 - 10.1109/TNNLS.2025.3622106

DO - 10.1109/TNNLS.2025.3622106

M3 - Journal article

SN - 2162-2388

VL - 37

SP - 1533

EP - 1545

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 4

ER -

Decentralized Online Optimization With Compressed Communication Over Directed Graphs

Abstract

UN SDGs

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this