Decentralized Stochastic Optimization over Unreliable Networks via Two-timescales Updates
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908433038442496 |
|---|---|
| author | Liu, Haoming Yau, Chung-Yiu Wai, Hoi-To |
| author_facet | Liu, Haoming Yau, Chung-Yiu Wai, Hoi-To |
| contents | This paper introduces a robust two-timescale compressed primal-dual (TiCoPD) algorithm tailored for decentralized optimization under bandwidth-limited and unreliable channels. By integrating the majorization-minimization approach with the primal-dual optimization framework, the TiCoPD algorithm strategically compresses the difference term shared among agents to enhance communication efficiency and robustness against noisy channels without compromising convergence stability. The method incorporates a mirror sequence for agent consensus on nonlinearly compressed terms updated on a fast timescale, together with a slow timescale primal-dual recursion for optimizing the objective function. Our analysis demonstrates that the proposed algorithm converges to a stationary solution when the objective function is smooth but possibly non-convex. Numerical experiments corroborate the conclusions of this paper. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08964 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decentralized Stochastic Optimization over Unreliable Networks via Two-timescales Updates Liu, Haoming Yau, Chung-Yiu Wai, Hoi-To Optimization and Control 68W15 G.1.6 This paper introduces a robust two-timescale compressed primal-dual (TiCoPD) algorithm tailored for decentralized optimization under bandwidth-limited and unreliable channels. By integrating the majorization-minimization approach with the primal-dual optimization framework, the TiCoPD algorithm strategically compresses the difference term shared among agents to enhance communication efficiency and robustness against noisy channels without compromising convergence stability. The method incorporates a mirror sequence for agent consensus on nonlinearly compressed terms updated on a fast timescale, together with a slow timescale primal-dual recursion for optimizing the objective function. Our analysis demonstrates that the proposed algorithm converges to a stationary solution when the objective function is smooth but possibly non-convex. Numerical experiments corroborate the conclusions of this paper. |
| title | Decentralized Stochastic Optimization over Unreliable Networks via Two-timescales Updates |
| topic | Optimization and Control 68W15 G.1.6 |
| url | https://arxiv.org/abs/2502.08964 |