Privacy Preserving Distributed Bandit Residual Feedback Online Optimization Over Time-Varying Unbalanced Graphs
文献类型：期刊论文
| 作者 | Zhongyuan Zhao; Zhiqiang Yang; Luyao Jiang; Ju Yang; Quanbo Ge |
| 刊名 | IEEE/CAA Journal of Automatica Sinica
 |
| 出版日期 | 2024 |
| 卷号 | 11期号:11页码:2284-2297 |
| 关键词 | Differential privacy distributed online optimization (DOO) federated learning one-point residual feedback (OPRF) time-varying unbalanced graphs |
| ISSN号 | 2329-9266 |
| DOI | 10.1109/JAS.2024.124656 |
| 英文摘要 | This paper considers the distributed online optimization (DOO) problem over time-varying unbalanced networks, where gradient information is explicitly unknown. To address this issue, a privacy-preserving distributed online one-point residual feedback (OPRF) optimization algorithm is proposed. This algorithm updates decision variables by leveraging one-point residual feedback to estimate the true gradient information. It can achieve the same performance as the two-point feedback scheme while only requiring a single function value query per iteration. Additionally, it effectively eliminates the effect of time-varying unbalanced graphs by dynamically constructing row stochastic matrices. Furthermore, compared to other distributed optimization algorithms that only consider explicitly unknown cost functions, this paper also addresses the issue of privacy information leakage of nodes. Theoretical analysis demonstrate that the method attains sublinear regret while protecting the privacy information of agents. Finally, numerical experiments on distributed collaborative localization problem and federated learning confirm the effectiveness of the algorithm. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59453]  |
| 专题 | 自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica |
| 推荐引用方式 GB/T 7714 | Zhongyuan Zhao,Zhiqiang Yang,Luyao Jiang,et al. Privacy Preserving Distributed Bandit Residual Feedback Online Optimization Over Time-Varying Unbalanced Graphs[J]. IEEE/CAA Journal of Automatica Sinica,2024,11(11):2284-2297. |
| APA | Zhongyuan Zhao,Zhiqiang Yang,Luyao Jiang,Ju Yang,&Quanbo Ge.(2024).Privacy Preserving Distributed Bandit Residual Feedback Online Optimization Over Time-Varying Unbalanced Graphs.IEEE/CAA Journal of Automatica Sinica,11(11),2284-2297. |
| MLA | Zhongyuan Zhao,et al."Privacy Preserving Distributed Bandit Residual Feedback Online Optimization Over Time-Varying Unbalanced Graphs".IEEE/CAA Journal of Automatica Sinica 11.11(2024):2284-2297. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。