Distributed Event-Triggered Bandit Convex Optimization With Time-Varying Constraints
- 8 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 12 (3) , 2242-2253
Abstract
This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violation. Existing distributed online algorithms solving this problem require that each agent broadcasts its decision to its neighbors at each iteration. However, communication resources are often limited. To better utilize communication resources, we propose a distributed event-triggered online primal–dual algorithm with two-point bandit feedback. Under several classes of appropriately chosen decreasing parameter sequences and non-increasing event-triggered threshold sequences, we establish dynamic network regret and network cumulative constraint violation bounds. These bounds are comparable to the results achieved by distributed event-triggered online algorithms with full-information feedback. Finally, a numerical example is provided to verify the theoretical results.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62133003)
- National Natural Science Foundation of China (62325304)
- National Natural Science Foundation of China (U22B2046)
- Knut och Alice Wallenbergs Stiftelse
- Swedish Foundation for Strategic Research
- Vetenskapsrådet
This publication has 30 references indexed in Scilit:
- Distributed online constrained convex optimization with event-triggered communicationEuropean Journal of Control, 2024
- A survey on distributed online optimization and online gamesAnnual Reviews in Control, 2023
- Event-triggered distributed online convex optimization with delayed bandit feedbackApplied Mathematics and Computation, 2023
- Distributed Online Mirror Descent Algorithm with Event Triggered CommunicationIFAC-PapersOnLine, 2022
- Distributed online bandit optimization under random quantizationAutomatica, 2022
- A survey of distributed optimizationAnnual Reviews in Control, 2019
- Decentralized event-triggered consensus for linear multi-agent systems under general directed graphsAutomatica, 2016
- Event-based broadcasting for multi-agent average consensusAutomatica, 2013
- Logarithmic regret algorithms for online convex optimizationMachine Learning, 2007
- Convex Optimization2004