Document Type

Article

Publication Title

arXiv

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. © 2022, CC BY.

DOI

10.48550/arXiv.2206.02009

Publication Date

6-4-2022

Keywords

As numbers, Central servers, Communication cost, Hessian-vector products, Low dimensional, Memory cost, Memory requirements, Newton-type methods, Second orders, Sketchings, Learning systems, Optimization and Control (math.OC)

Comments

Preprint: arXiv

Archived with thanks to arXiv

Preprint License: CC by 4.0

Uploaded 13 July 2022

Download

Share

COinS