Abstract | ||
---|---|---|
Federated learning involves a mixture of centralized and decentralized processing tasks, where a server regularly selects a sample of the agents and these in turn sample their local data to compute stochastic gradients for their learning updates. The sampling of both agents and data is generally uniform; however, in this work we consider non-uniform sampling. We derive optimal importance sampling strategies for both agent and data selection and show that under convexity and Lipschitz assumptions, non-uniform sampling without replacement improves the performance of the original FedAvg algorithm. We run experiments on a regression and classification problem to illustrate the theoretical results. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICASSP39728.2021.9413655 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
federated learning, importance sampling, asynchronous SGD, non-IID data, heterogeneous agents | Conference | 0 |
PageRank | References | Authors |
0.34 | 1 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Elsa Rizk | 1 | 0 | 0.34 |
Stefan Vlaski | 2 | 23 | 11.39 |
Ali H. Sayed | 3 | 9134 | 667.71 |