Adaptive Federated Learning with Auto-Tuned Clients
This addresses the problem of variable client conditions in federated learning, but it is incremental as it builds on existing SGD methods.
The paper tackles the challenge of hyperparameter tuning in federated learning by proposing Δ-SGD, a step size rule that allows clients to adapt to local smoothness, showing benefits in various scenarios.
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.