AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

Federated Automatic Differentiation

Keith Rush, Zachary Charles, Zachary Garrett

JMLR 2024 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
learn server learning rate and momentum by federated hypergradient descent (ablation)FedAvgM · SO NWP (default server init, random client LR)max test accuracy (%): 25.0 -> 25.7Improved
learn server learning rate and momentum by federated hypergradient descent (ablation)FedAvgM · Shakespeare (default server init, random client LR)max test accuracy (%): 56.8 -> 57.3Improved
learn server learning rate and momentum by federated hypergradient descent (ablation)FedAvgM · EMNIST (default server init, random client LR)max test accuracy (%): 87.0 -> 87.1Improved
learn server learning rate and momentum by federated hypergradient descent (ablation)FedAvgM · CIFAR-100 (default server init, random client LR)max test accuracy (%): 43.2 -> 45.6Improved
learn server learning rate and momentum by federated hypergradient descent (ablation)FedAvgM · SO TP (recall@5) (default server init, random client LR)max test accuracy (%): 32.2 -> 35.8Improved
learn server hyperparameters instead of fixing them at defaults (default server/default client) (ablation)FedAvgM on SO NWP · SO NWPruns diverged early: 23/50 -> noneImproved
use learned hyperparameters to reach unlearned max accuracy with fewer trialsFedAvgM · bootstrap over 50 trialstrials needed: one-tenth the trialsImproved
learn client weighting exponent instead of example weighting (ablation)FedAvg · CIFAR-100, EMNIST, Shakespeare, SO NWP, SO TPtest performanceNo clear effect
learn client weighting exponent instead of fixed example or uniform weighting (ablation)FedAvg · Synthetic(1,1)lossImproved
initialize learned weighting exponent at q=0 instead of q=1 (ablation)FedAvg with learned weighting · Synthetic(1,1)lossHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy