Two-timescale EXTRA for Distributed Smooth Non-convex Optimization
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_ | 1866918144586547200 |
|---|---|
| author | Peng, Zeyu Farokhi, Farhad Pu, Ye |
| author_facet | Peng, Zeyu Farokhi, Farhad Pu, Ye |
| contents | In this paper, we study distributed optimization with smooth non-convex local objectives. We propose a novel variant of the well-known EXact firsT-ordeR Algorithm (EXTRA), called Two-timescale EXTRA, by introducing two distinct step-sizes. Leveraging the two-timescale strategy, we construct a Lyapunov function and establish the sub-linear convergence of Two-timescale EXTRA to a consensual first-order stationary point. Additionally, we introduce an off-line sequential method for algorithm parameter selection, and the numerical results support the theoretical guarantees. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_19483 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Two-timescale EXTRA for Distributed Smooth Non-convex Optimization Peng, Zeyu Farokhi, Farhad Pu, Ye Optimization and Control In this paper, we study distributed optimization with smooth non-convex local objectives. We propose a novel variant of the well-known EXact firsT-ordeR Algorithm (EXTRA), called Two-timescale EXTRA, by introducing two distinct step-sizes. Leveraging the two-timescale strategy, we construct a Lyapunov function and establish the sub-linear convergence of Two-timescale EXTRA to a consensual first-order stationary point. Additionally, we introduce an off-line sequential method for algorithm parameter selection, and the numerical results support the theoretical guarantees. |
| title | Two-timescale EXTRA for Distributed Smooth Non-convex Optimization |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2411.19483 |