Distributed zeroth-order online optimization with communication delays

Inoue, Keito; Hayashi, Naoki; Takai, Shigemasa

IET Control Theory and Applications, 2025, 19(1), e12759

アクセス数:436件（2025-09-20 01:10 集計）

固定URL: https://hdl.handle.net/11094/100341

閲覧可能ファイル 

ファイル フォーマット 利用条件 サイズ 閲覧回数 利用開始日 説明 information
IETControlTheoryAppl_19_1_e12759 pdf なし 1.24 MB 24 2025.02.18  
Creative Commons : 表示 - 非営利

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル
Distributed zeroth-order online optimization with communication delays
著者
著者名
Inoue, Keito
NRID
1000080637752 1000080637752
researchmap permalink
zu3rv2h zu3rv2h
Scopus Author ID
30967580300 30967580300
著者名
Hayashi, Naoki
NRID
1000060243177 1000060243177
researchmap permalink
read0014096 read0014096
Scopus Author ID
7201470914 7201470914
著者名
Takai, Shigemasa
キーワード等
bandit feedback
communication delays
distributed online optimization
multiagent system
内容
Inoue K., Hayashi N., Takai S. Distributed zeroth-order online optimization with communication delays. IET Control Theory and Applications 19, e12759 (2025); https://doi.org/10.1049/cth2.12759.
抄録
This paper investigates distributed online optimization in a networked multiagent system, where each agent has its own private objective and constraint functions that vary over time. In many real-world scenarios, computing the gradient of the cost function can be challenging, especially when agents have limited computational capabilities. Moreover, communication delays are common in practical networked systems due to various factors. This paper considers a unified framework for distributed online optimization that can handle bandit feedback and communication delays feedback simultaneously. A distributed primal-dual algorithm is proposed that utilizes bandit feedback, in which the agents estimate the gradients of their objective and constraint functions by sampling the function values. An enlarged network model that incorporates the delayed information exchanged among the agents is introduced. Through theoretical analysis, it is shown that the proposed algorithm achieves sublinear upper bounds on both the dynamic regret and the constraint violation despite communication delays.
出版者
John Wiley and Sons Inc
収録物名
IET Control Theory and Applications
巻(号)
19(1)
ページ
e12759
刊行年月
2025-01-02
言語
英語
ハンドルURL
https://hdl.handle.net/11094/100341
PISSN
17518644
eISSN
17518652
関連情報 (isIdenticalTo)
DOI (出版社版)
https://doi.org/10.1049/cth2.12759
アクセス権
open access
権利情報
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
出版タイプ
Version of Record
カテゴリ
学術雑誌論文 Journal Article