Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.05529 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929237831712768 |
|---|---|
| author | Rizk, Elsa Yuan, Kun Sayed, Ali H. |
| author_facet | Rizk, Elsa Yuan, Kun Sayed, Ali H. |
| contents | In this work, we examine a network of agents operating asynchronously, aiming to discover an ideal global model that suits individual local datasets. Our assumption is that each agent independently chooses when to participate throughout the algorithm and the specific subset of its neighbourhood with which it will cooperate at any given moment. When an agent chooses to take part, it undergoes multiple local updates before conveying its outcomes to the sub-sampled neighbourhood. Under this setup, we prove that the resulting asynchronous diffusion strategy is stable in the mean-square error sense and provide performance guarantees specifically for the federated learning setting. We illustrate the findings with numerical simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05529 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Asynchronous Diffusion Learning with Agent Subsampling and Local Updates Rizk, Elsa Yuan, Kun Sayed, Ali H. Machine Learning Multiagent Systems In this work, we examine a network of agents operating asynchronously, aiming to discover an ideal global model that suits individual local datasets. Our assumption is that each agent independently chooses when to participate throughout the algorithm and the specific subset of its neighbourhood with which it will cooperate at any given moment. When an agent chooses to take part, it undergoes multiple local updates before conveying its outcomes to the sub-sampled neighbourhood. Under this setup, we prove that the resulting asynchronous diffusion strategy is stable in the mean-square error sense and provide performance guarantees specifically for the federated learning setting. We illustrate the findings with numerical simulations. |
| title | Asynchronous Diffusion Learning with Agent Subsampling and Local Updates |
| topic | Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2402.05529 |