Constant-Stepsize Distributed Optimization Algorithm with Malicious Nodes

Shiheng Zhang, Zhi Wei Liu, Yang Zhai, Yu Zhao, Guanghui Wen

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

This paper develops a consensus-based distributed (sub)gradient descent algorithm, which has a faster convergence rate in the presence of malicious nodes. To achieve this, two main methods are used in the proposed algorithm. The first is using the local filtering algorithm to counteract the attacks of malicious nodes; The second is using the constant step size in the distributed (sub)gradient descent algorithm rather than diminishing step size to accelerate the convergence rate. As a result, the proposed algorithm improves the convergence rate in the presence of malicious nodes. Finally, a numerical example is presented to verify the proposed algorithm, and the possible future research directions are given.

源语言英语
主期刊名2021 International Conference on Neuromorphic Computing, ICNC 2021
出版商Institute of Electrical and Electronics Engineers Inc.
177-182
页数6
ISBN(电子版)9781665412872
DOI
出版状态已出版 - 2021
已对外发布
活动2021 International Conference on Neuromorphic Computing, ICNC 2021 - Wuhan, 中国
期限: 15 10月 202117 10月 2021

出版系列

姓名2021 International Conference on Neuromorphic Computing, ICNC 2021

会议

会议2021 International Conference on Neuromorphic Computing, ICNC 2021
国家/地区中国
Wuhan
时期15/10/2117/10/21

指纹

探究 'Constant-Stepsize Distributed Optimization Algorithm with Malicious Nodes' 的科研主题。它们共同构成独一无二的指纹。

引用此