Federated dual averaging learning algorithm with delayed gradients for composite optimization

DOI10.1016/J.INS.2024.121223MaRDI QIDQ6658933zbMATH OpenFDO

Authors Jueyou Li, Jia Wang, Yu-Qi Hao

Publication date 8 January 2025

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.INS.2024.121223

zbMATH Keywords

dual averagingcomposite optimizationfederated learningdelayed gradients

Mathematics Subject Classification ID

Computer science (68-XX) Operations research, mathematical programming (90-XX)

Recommendations

• Privacy-preserving and communication-efficient stochastic alternating direction method of multipliers for federated learning
• Federated primal dual fixed point algorithm
• Cooperative convex optimization with subgradient delays using push-sum distributed dual averaging
• A stochastic averaging gradient algorithm with multi‐step communication for distributed optimization

Cites work

• An Asynchronous Mini-Batch Algorithm for Regularized Stochastic Optimization
• Communication-efficient and privacy-preserving large-scale federated learning counteracting heterogeneity
• Decentralized consensus algorithm with delayed and stochastic gradients
• Distributed optimization for multi-agent systems with constraints set and communication time-delay over a directed graph
• Exact matrix completion via convex optimization
• Online distributed dual averaging algorithm for multi-agent bandit optimization over time-varying general directed networks
• RTGA: robust ternary gradients aggregation for federated learning
• Regression Shrinkage and Selection via The Lasso: A Retrospective
• Regularization and Variable Selection Via the Elastic Net
• Sparse inverse covariance estimation with the graphical lasso

This page was built for publication: Federated dual averaging learning algorithm with delayed gradients for composite optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6658933)