Convergence Rate of Projected Subgradient Method with Time-varying Step-sizes
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929532085207040 |
|---|---|
| author | Zhu, Zhihan Zhang, Yanhao Xia, Yong |
| author_facet | Zhu, Zhihan Zhang, Yanhao Xia, Yong |
| contents | We establish the optimal ergodic convergence rate for the classical projected subgradient method with a time-varying step-size. This convergence rate remains the same even if we slightly increase the weight of the most recent points, thereby relaxing the ergodic sense. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10221 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Convergence Rate of Projected Subgradient Method with Time-varying Step-sizes Zhu, Zhihan Zhang, Yanhao Xia, Yong Optimization and Control 90C25, 90C30 We establish the optimal ergodic convergence rate for the classical projected subgradient method with a time-varying step-size. This convergence rate remains the same even if we slightly increase the weight of the most recent points, thereby relaxing the ergodic sense. |
| title | Convergence Rate of Projected Subgradient Method with Time-varying Step-sizes |
| topic | Optimization and Control 90C25, 90C30 |
| url | https://arxiv.org/abs/2402.10221 |