Distributed Event-Triggered Bandit Convex Optimization with Time-Varying Constraints
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913398418046976 |
|---|---|
| author | Zhang, Kunpeng Yi, Xinlei Wen, Guanghui Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao |
| author_facet | Zhang, Kunpeng Yi, Xinlei Wen, Guanghui Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao |
| contents | 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 require that each agent broadcasts its decision to its neighbors at each iteration. To better utilize the limited 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14060 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Distributed Event-Triggered Bandit Convex Optimization with Time-Varying Constraints Zhang, Kunpeng Yi, Xinlei Wen, Guanghui Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao Optimization and Control 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 require that each agent broadcasts its decision to its neighbors at each iteration. To better utilize the limited 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. |
| title | Distributed Event-Triggered Bandit Convex Optimization with Time-Varying Constraints |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2406.14060 |