A tight convergence analysis for stochastic gradient descent with delayed updates

MaRDI QIDQ7025150zbMATH OpenFDO

Authors Yossi Arjevani, Ohad Shamir, Nathan Srebro

Publication date 19 February 2025

Full work available at URL https://proceedings.mlr.press/v117/arjevani20a.html

zbMATH Keywords

asynchronousdelayedlower boundsoptimizationstochastic gradient descentupper bounds

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15)

Cites work

• An Asynchronous Mini-Batch Algorithm for Regularized Stochastic Optimization
• An optimal randomized incremental gradient method
• Analytic combinatorics
• Convex optimization: algorithms and complexity
• Distributed asynchronous incremental subgradient methods
• How bad are Vandermonde matrices?
• scientific article; zbMATH DE number 3983158 (Why is no real title available?)
• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• scientific article; zbMATH DE number 51132 (Why is no real title available?)
• Improved asynchronous parallel optimization analysis for stochastic incremental methods
• Introductory lectures on convex optimization. A basic course.
• On lower and upper bounds in smooth and strongly convex optimization
• Optimal distributed online prediction using mini-batches

Cited in

(1)

• PersA-FL  : personalized asynchronous federated learning

This page was built for publication: A tight convergence analysis for stochastic gradient descent with delayed updates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7025150)