A Zeroth-order Resilient Algorithm for Distributed Online Optimization against Byzantine Edge Attacks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911253623996416 |
|---|---|
| author | Liu, Yuhang Mei, Wenjun |
| author_facet | Liu, Yuhang Mei, Wenjun |
| contents | In this paper, we propose a zeroth-order resilient distributed online algorithm for networks under Byzantine edge attacks. We assume that both the edges attacked by Byzantine adversaries and the objective function are time-varying. Moreover, we focus on the scenario where the complete time-varying objective function cannot be observed, and only its value at a certain point is available. Using deterministic difference, we design a zeroth-order distributed online optimization algorithm against Byzantine edge attacks and provide an upper bound on the dynamic regret of the algorithm. Finally, a simulation example is given justifying the theoretical results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05104 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Zeroth-order Resilient Algorithm for Distributed Online Optimization against Byzantine Edge Attacks Liu, Yuhang Mei, Wenjun Optimization and Control In this paper, we propose a zeroth-order resilient distributed online algorithm for networks under Byzantine edge attacks. We assume that both the edges attacked by Byzantine adversaries and the objective function are time-varying. Moreover, we focus on the scenario where the complete time-varying objective function cannot be observed, and only its value at a certain point is available. Using deterministic difference, we design a zeroth-order distributed online optimization algorithm against Byzantine edge attacks and provide an upper bound on the dynamic regret of the algorithm. Finally, a simulation example is given justifying the theoretical results. |
| title | A Zeroth-order Resilient Algorithm for Distributed Online Optimization against Byzantine Edge Attacks |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2511.05104 |