Distributed Online Randomized Gradient-Free optimization with Compressed Communication
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908349104128000 |
|---|---|
| author | Zhu, Longkang Shi, Xinli Xu, Xiangping Cao, Jinde |
| author_facet | Zhu, Longkang Shi, Xinli Xu, Xiangping Cao, Jinde |
| contents | This paper addresses two fundamental challenges in distributed online convex optimization: communication efficiency and optimization under limited feedback. We propose Online Compressed Gradient Tracking with one-point Bandit Feedback (OCGT-BF), a novel algorithm that harness data compression and gradient-free optimization techniques in distributed networks. Our algorithm incorporates a compression scheme with error compensation mechanisms to reduce communication overhead while maintaining convergence guarantees. Unlike traditional approaches that assume perfect communication and full gradient access, OCGT-BF operates effectively under practical constraints by combining gradient-like tracking with one-point feedback estimation. We provide theoretical analysis demonstrating the dynamic regret bounds under both bandit feedback and stochastic gradient scenarios. Finally, extensive experiments validate that OCGT-BF achieves low dynamic regret while significantly reducing communication requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_21693 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Distributed Online Randomized Gradient-Free optimization with Compressed Communication Zhu, Longkang Shi, Xinli Xu, Xiangping Cao, Jinde Optimization and Control This paper addresses two fundamental challenges in distributed online convex optimization: communication efficiency and optimization under limited feedback. We propose Online Compressed Gradient Tracking with one-point Bandit Feedback (OCGT-BF), a novel algorithm that harness data compression and gradient-free optimization techniques in distributed networks. Our algorithm incorporates a compression scheme with error compensation mechanisms to reduce communication overhead while maintaining convergence guarantees. Unlike traditional approaches that assume perfect communication and full gradient access, OCGT-BF operates effectively under practical constraints by combining gradient-like tracking with one-point feedback estimation. We provide theoretical analysis demonstrating the dynamic regret bounds under both bandit feedback and stochastic gradient scenarios. Finally, extensive experiments validate that OCGT-BF achieves low dynamic regret while significantly reducing communication requirements. |
| title | Distributed Online Randomized Gradient-Free optimization with Compressed Communication |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2504.21693 |