Year: 2020
Type: preprint
Abstract: We propose a new optimization formulation for training federated learning models. The standard formulation has the form of an empirical risk minimization problem constructed to find a single global model trained from the private data stored across all participating devices. In contrast, our formulation seeks an explicit trade-off between this traditional global model and the local models, which can be learned by each device from its own private data without any communication. Further, we develop several efficient variants of SGD (with and without partial participation and with and without variance reduction) for solving the new formulation and prove communication complexity guarantees. Notably, our methods are similar but not identical to federated averaging / local SGD, thus shedding some light on the role of local steps in federated learning. In particular, we are the first to i) show that local steps can improve communication for problems with heterogeneous data, and ii) point out that personalization yields reduced communication complexity.
Source: arXiv (Cornell University)
Authors: Hanzely, Filip, Richtárik, Peter
Institution: King Abdullah University of Science and Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3005776401
