Provable Reduction in Communication Rounds for Non-Smooth Convex Federated Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913762716418048 |
|---|---|
| author | Palenzuela, Karlo Dadras, Ali Yurtsever, Alp Löfstedt, Tommy |
| author_facet | Palenzuela, Karlo Dadras, Ali Yurtsever, Alp Löfstedt, Tommy |
| contents | Multiple local steps are key to communication-efficient federated learning. However, theoretical guarantees for such algorithms, without data heterogeneity-bounding assumptions, have been lacking in general non-smooth convex problems. Leveraging projection-efficient optimization methods, we propose FedMLS, a federated learning algorithm with provable improvements from multiple local steps. FedMLS attains an $ε$-suboptimal solution in $\mathcal{O}(1/ε)$ communication rounds, requiring a total of $\mathcal{O}(1/ε^2)$ stochastic subgradient oracle calls. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21627 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Provable Reduction in Communication Rounds for Non-Smooth Convex Federated Learning Palenzuela, Karlo Dadras, Ali Yurtsever, Alp Löfstedt, Tommy Machine Learning Optimization and Control Multiple local steps are key to communication-efficient federated learning. However, theoretical guarantees for such algorithms, without data heterogeneity-bounding assumptions, have been lacking in general non-smooth convex problems. Leveraging projection-efficient optimization methods, we propose FedMLS, a federated learning algorithm with provable improvements from multiple local steps. FedMLS attains an $ε$-suboptimal solution in $\mathcal{O}(1/ε)$ communication rounds, requiring a total of $\mathcal{O}(1/ε^2)$ stochastic subgradient oracle calls. |
| title | Provable Reduction in Communication Rounds for Non-Smooth Convex Federated Learning |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2503.21627 |