FLECS: A Federated Learning Second-Order Framework via Compression and Sketching

arXiv2206.02009MaRDI QIDQ6401130FDOQ6401130

Authors: Artem Agafonov, Dmitry Kamzolov, Rachael Tappenden, A. V. Gasnikov, M. Takáč 

Publication date: 4 June 2022

Abstract: Inspired by the recent work FedNL (Safaryan et al, FedNL: Making Newton-Type Methods Applicable to Federated Learning), we propose a new communication efficient second-order framework for Federated learning, namely FLECS. The proposed method reduces the high-memory requirements of FedNL by the usage of an L-SR1 type update for the Hessian approximation which is stored on the central server. A low dimensional `sketch' of the Hessian is all that is needed by each device to generate an update, so that memory costs as well as number of Hessian-vector products for the agent are low. Biased and unbiased compressions are utilized to make communication costs also low. Convergence guarantees for FLECS are provided in both the strongly convex, and nonconvex cases, and local linear convergence is also established under strong convexity. Numerical experiments confirm the practical benefits of this new FLECS algorithm.

This page was built for publication: FLECS: A Federated Learning Second-Order Framework via Compression and Sketching

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6401130)