TY - GEN
T1 - Distributed Online Convex Optimization with Adaptive Event-Triggered Scheme
AU - Suo, Wei
AU - Li, Wenling
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - This paper is concerned with the distributed online convex optimization problem in which a series of agents try to track the minimizer of a global convex function. A consensus then adaptive with gradient exchange (CTAGE) algorithm is proposed where the gradient information exchanged among agents is adopted to facilitate reaching consensus. To alleviate the communication overhead among agents, an adaptive event-Triggered scheme (AETS) is adopted, which can dynamically adjust the threshold. Specifically, the threshold would hold when there are consecutive triggers, and it would decrease while the triggering condition is not satisfied for several steps. Then, theoretical results indicate that dynamic regret of CTAGE can reach sublinear upper bound. Finally, a target tracking example is utilized to demonstrate the usefulness of the proposed algorithm.
AB - This paper is concerned with the distributed online convex optimization problem in which a series of agents try to track the minimizer of a global convex function. A consensus then adaptive with gradient exchange (CTAGE) algorithm is proposed where the gradient information exchanged among agents is adopted to facilitate reaching consensus. To alleviate the communication overhead among agents, an adaptive event-Triggered scheme (AETS) is adopted, which can dynamically adjust the threshold. Specifically, the threshold would hold when there are consecutive triggers, and it would decrease while the triggering condition is not satisfied for several steps. Then, theoretical results indicate that dynamic regret of CTAGE can reach sublinear upper bound. Finally, a target tracking example is utilized to demonstrate the usefulness of the proposed algorithm.
KW - Adaptive event-Triggered scheme
KW - Distributed online optimization
KW - Dynamic regret
UR - https://www.scopus.com/pages/publications/85165998939
U2 - 10.1109/DDCLS58216.2023.10166694
DO - 10.1109/DDCLS58216.2023.10166694
M3 - 会议稿件
AN - SCOPUS:85165998939
T3 - Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023
SP - 33
EP - 38
BT - Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2023
Y2 - 12 May 2023 through 14 May 2023
ER -