Byzantine-Resilient Distributed Bandit Online Optimization in Dynamic Environments
IEEE Transactions on Industrial Cyber-Physical Systems · 2024 · 2 · 154-165
DOI: 10.1109/ticps.2024.3410846 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Industrial Cyber-Physical Systems, 2024. Verfasst von Mengli Wei und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Science and Technology Major Project of China, National Natural Science Foundation of China, Jiangsu Provincial Scientific Research Center of Applied Mathematics.
Abstract (Originalsprache)
We consider the constrained multi-agent online optimization problem in dynamic environments that are vulnerable to Byzantine attacks, where some infiltrated agents may deviate from the prescribed update rule and send arbitrary messages. The objective functions are exposed in a bandit form, i.e., only the function value is revealed to each agent at the sampling instance, and held privately by each agent. The agents only exchange information with their neighbors to update decisions, and the collective goal is to minimize the sum of the unattacked agents' objective functions in dynamic environments, where the same function can only be sampled once. To handle this problem, a Byzantine-Resilient Distributed Bandit Online Convex Optimization (BR-DBOCO) algorithm that can tolerate up to $\mathcal {B}$ Byzantine agents is developed. Specifically, the BR-DBOCO employs the one-point bandit feedback (OPBF) mechanism and state filter to cope with the objective function, which cannot be explicitly expressed in dynamic environments and the arbitrary deviation states caused by Byzantine attacks, respectively. We show that sublinear expected regret is achieved if the accumulative deviation of the comparator sequence also grows sublinearly with a proper exploration parameter. Finally, experimental results are presented to illustrate the effectiveness of the proposed algorithm.
Förderung
- National Science and Technology Major Project of China
- National Natural Science Foundation of China
- Jiangsu Provincial Scientific Research Center of Applied Mathematics
Zitieren
APA
Wei, M., Yu, W., Liu, H., & Chen, D. (2024). Byzantine-Resilient Distributed Bandit Online Optimization in Dynamic Environments. IEEE Transactions on Industrial Cyber-Physical Systems, 2, 154-165. https://doi.org/10.1109/ticps.2024.3410846
Vancouver
Wei M, Yu W, Liu H, Chen D. Byzantine-Resilient Distributed Bandit Online Optimization in Dynamic Environments. IEEE Transactions on Industrial Cyber-Physical Systems. 2024;2:154-165. doi:10.1109/ticps.2024.3410846
BibTeX
@article{Wei2024,
author = {Wei, Mengli and Yu, Wenwu and Liu, Hongzhe and Chen, Duxin},
title = {Byzantine-Resilient Distributed Bandit Online Optimization in Dynamic Environments},
journal = {IEEE Transactions on Industrial Cyber-Physical Systems},
year = {2024},
volume = {2},
pages = {154--165},
doi = {10.1109/ticps.2024.3410846}
}
EUVIMED