AI Paper Atlas

Research map / Optimization / Distributed and compressed

Federated Accelerated Stochastic Gradient Descent

Honglin Yuan, Tengyu Ma

NeurIPS 2020 · Optimization › Distributed and compressed · approach: Local and asynchronous SGD

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
Use FedAc-I instead of FedAvgDistributed stochastic optimization · Strongly convex, smooth objectivescommunication overhead term: \frac{L \sigma^2}{\mu^2 T R} -> \frac{L \sigma^2}{\mu^2 T R^2}Improved
Use FedAc-II instead of FedAvgDistributed stochastic optimization · Strongly convex, smooth objectivescommunication overhead term: \frac{L \sigma^2}{\mu^2 T R} -> \frac{L^2 \sigma^2}{\mu^3 T R^3}Improved
Use FedAc instead of FedAvgDistributed stochastic optimization · General convex objectivescommunication-dependent convergence term: \frac{1}{T^{\frac{1}{3}} R^{\frac{1}{3}}} -> \frac{1}{T^{\frac{1}{3}} R^{\frac{2}{3}}}Improved
Use FedAc instead of Minibatch-SGDDistributed stochastic optimization · General convex objectivescommunication-dependent convergence term: \frac{1}{R} -> \frac{1}{T^{\frac{1}{3}} R^{\frac{2}{3}}}Improved
Apply FedAc-II under third-order smoothness instead of FedAvgDistributed stochastic optimization · Strongly convex, third-order-smooth objectivescommunication overhead term: \frac{Q^2 \sigma^4}{\mu^5 T^2 R^2} -> \frac{Q^2 \sigma^4}{\mu^5 T^2 R^6}Improved
Use FedAc-I rather than FedAvgLogistic regression · a9a, 8192 workers, suboptimality 10^{-3}communication rounds: 4096 -> 32Improved
Use FedAc-I rather than Minibatch-SGDLogistic regression · a9a, 8192 workers, suboptimality 10^{-3}communication rounds: 1024 -> 32Improved
Use FedAc-I rather than Minibatch-Accelerated-SGDLogistic regression · a9a, 8192 workers, suboptimality 10^{-3}communication rounds: 128 -> 32Improved
Use FedAc-I rather than FedAvgLogistic regression · epsilon, 2048 workers, suboptimality 10^{-4}communication rounds: 4096 -> 64Improved
Use FedAc-I rather than Minibatch-SGDLogistic regression · epsilon, 2048 workers, suboptimality 10^{-4}communication rounds: 4096 -> 64Improved
Use FedAc-I rather than Minibatch-Accelerated-SGDLogistic regression · epsilon, 2048 workers, suboptimality 10^{-4}communication rounds: 256 -> 64Improved
Remove the acceleration-stability tradeoff and use full acceleration (ablation)FedAc · Direct parallelization with infrequent synchronizationstabilityHurt

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