AWhat changed
Used server-computed optimizer statistics during each client update, with an SVRG-style correction in Mime, to approximate centralized optimization while reducing client drift.
Scientific scope
Used server-computed optimizer statistics during each client update, with an SVRG-style correction in Mime, to approximate centralized optimization while reducing client drift. Distinct from server-only FedOpt and persistent-client SCAFFOLD. Inherits variance reduction and centralized momentum/adaptive optimizers. The base method must decompose into the specified update/statistics maps; theory uses bounded gradient/Hessian dissimilarity and smoothness regimes. Mimicking does not mean identical centralized trajectories or guarantees for every optimizer, and extra full local-gradient work has a cost.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Distinct from server-only FedOpt and persistent-client SCAFFOLD. Inherits variance reduction and centralized momentum/adaptive optimizers. The base method must decompose into the specified update/statistics maps; theory uses bounded gradient/Hessian dissimilarity and smoothness regimes. Mimicking does not mean identical centralized trajectories or guarantees for every optimizer, and extra full local-gradient work has a cost.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction