Adaptive Federated Learning with Auto-Tuned Clients
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929333103230976 |
|---|---|
| author | Kim, Junhyung Lyle Toghani, Mohammad Taha Uribe, César A. Kyrillidis, Anastasios |
| author_facet | Kim, Junhyung Lyle Toghani, Mohammad Taha Uribe, César A. Kyrillidis, Anastasios |
| contents | Federated learning (FL) is a distributed machine learning framework where the global model of a central server is trained via multiple collaborative steps by participating clients without sharing their data. While being a flexible framework, where the distribution of local data, participation rate, and computing power of each client can greatly vary, such flexibility gives rise to many new challenges, especially in the hyperparameter tuning on the client side. We propose $Δ$-SGD, a simple step size rule for SGD that enables each client to use its own step size by adapting to the local smoothness of the function each client is optimizing. We provide theoretical and empirical results where the benefit of the client adaptivity is shown in various FL scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_11201 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Adaptive Federated Learning with Auto-Tuned Clients Kim, Junhyung Lyle Toghani, Mohammad Taha Uribe, César A. Kyrillidis, Anastasios Machine Learning Distributed, Parallel, and Cluster Computing Optimization and Control Federated learning (FL) is a distributed machine learning framework where the global model of a central server is trained via multiple collaborative steps by participating clients without sharing their data. While being a flexible framework, where the distribution of local data, participation rate, and computing power of each client can greatly vary, such flexibility gives rise to many new challenges, especially in the hyperparameter tuning on the client side. We propose $Δ$-SGD, a simple step size rule for SGD that enables each client to use its own step size by adapting to the local smoothness of the function each client is optimizing. We provide theoretical and empirical results where the benefit of the client adaptivity is shown in various FL scenarios. |
| title | Adaptive Federated Learning with Auto-Tuned Clients |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing Optimization and Control |
| url | https://arxiv.org/abs/2306.11201 |