Federated Accelerated Stochastic Gradient Descent

arXiv2006.08950MaRDI QIDQ6343011

Author name not available (Why is that?)

Publication date: 16 June 2020

Abstract: We propose Federated Accelerated Stochastic Gradient Descent (FedAc), a principled acceleration of Federated Averaging (FedAvg, also known as Local SGD) for distributed optimization. FedAc is the first provable acceleration of FedAvg that improves convergence speed and communication efficiency on various types of convex functions. For example, for strongly convex and smooth functions, when using $M$ workers, the previous state-of-the-art FedAvg analysis can achieve a linear speedup in $M$ if given $M$ rounds of synchronization, whereas FedAc only requires $M^{frac13}$ rounds. Moreover, we prove stronger guarantees for FedAc when the objectives are third-order smooth. Our technique is based on a potential-based perturbed iterate analysis, a novel stability analysis of generalized accelerated SGD, and a strategic tradeoff between acceleration and stability.

Has companion code repository: https://github.com/hongliny/FedAc-NeurIPS20

This page was built for publication: Federated Accelerated Stochastic Gradient Descent

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6343011)