What is recorded here?
Separated client and server optimizers and treated average local model deltas as server pseudo-gradients, instantiating per-coordinate Adagrad, Adam and Yogi-style federated updates.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Inherits the underlying optimizers and FedAvg, not their reinvention. Original v1 main analysis assumes full client participation, bounded gradients/variance/heterogeneity and controlled client steps; broader participation extensions are discussed separately. Nonconvex stationarity and empirical gains do not imply unbiased global gradients, arbitrary tuning robustness or global optima.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Sashank J. Reddi; Zachary Charles; Manzil Zaheer; Zachary Garrett; Keith Rush; Jakub Konečný; Sanjiv Kumar; H. Brendan McMahan
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.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
FedOpt/FedAdam/FedYogi: adaptive server updates on federated model deltas
Separated client and server optimizers and treated average local model deltas as server pseudo-gradients, instantiating per-coordinate Adagrad, Adam and Yogi-style federated updates.
Scientific scope
Inherits the underlying optimizers and FedAvg, not their reinvention. Original v1 main analysis assumes full client participation, bounded gradients/variance/heterogeneity and controlled client steps; broader participation extensions are discussed separately. Nonconvex stationarity and empirical gains do not imply unbiased global gradients, arbitrary tuning robustness or global optima.
People and systems
Sashank J. Reddi; Zachary Charles; Manzil Zaheer; Zachary Garrett; Keith Rush; Jakub Konečný; Sanjiv Kumar; H. Brendan McMahan