Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.02538 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914017439645696 |
|---|---|
| author | Zhang, Rui Mou, Wenlong |
| author_facet | Zhang, Rui Mou, Wenlong |
| contents | In federated learning, communication cost can be significantly reduced by transmitting the information over the air through physical channels. In this paper, we propose a new class of adaptive federated stochastic gradient descent (SGD) algorithms that can be implemented over physical channels, taking into account both channel noise and hardware constraints. We establish theoretical guarantees for the proposed algorithms, demonstrating convergence rates that are adaptive to the stochastic gradient noise level. We also demonstrate the practical effectiveness of our algorithms through simulation studies with deep learning models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02538 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Federated learning over physical channels: adaptive algorithms with near-optimal guarantees Zhang, Rui Mou, Wenlong Machine Learning Information Theory Signal Processing In federated learning, communication cost can be significantly reduced by transmitting the information over the air through physical channels. In this paper, we propose a new class of adaptive federated stochastic gradient descent (SGD) algorithms that can be implemented over physical channels, taking into account both channel noise and hardware constraints. We establish theoretical guarantees for the proposed algorithms, demonstrating convergence rates that are adaptive to the stochastic gradient noise level. We also demonstrate the practical effectiveness of our algorithms through simulation studies with deep learning models. |
| title | Federated learning over physical channels: adaptive algorithms with near-optimal guarantees |
| topic | Machine Learning Information Theory Signal Processing |
| url | https://arxiv.org/abs/2509.02538 |