Optimal and efficient algorithms for decentralized online convex optimization

MaRDI QIDQ6887425zbMATH OpenFDO

Authors Yuanyu Wan, Xue Bo, M. L. Song, Lijun Zhang

Publication date 9 December 2025

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/24-2137.html

zbMATH Keywords

accelerated gossip strategydecentralized optimizationefficient algorithmsonline convex optimizationoptimal regret

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Convex programming (90C25)

Cites work

• A Linearly Convergent Variant of the Conditional Gradient Algorithm under Strong Convexity, with Applications to Online and Stochastic Optimization
• A primal-dual perspective of online learning algorithms
• Adaptive routing with end-to-end feedback: distributed learning and geometric approaches
• Beyond the regret minimization barrier: optimal algorithms for stochastic strongly-convex optimization
• Decentralized and parallel primal and dual accelerated methods for stochastic convex programming problems
• Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
• Fast linear iterations for distributed averaging
• scientific article; zbMATH DE number 5454133 (Why is no real title available?)
• scientific article; zbMATH DE number 1999062 (Why is no real title available?)
• Logarithmic regret algorithms for online convex optimization
• On the Generalization Ability of On-Line Learning Algorithms
• Online learning and online convex optimization
• Online linear optimization and adaptive routing
• Optimal convergence rates for convex distributed optimization in networks
• Optimal gradient tracking for decentralized optimization
• Primal-dual subgradient methods for convex problems

This page was built for publication: Optimal and efficient algorithms for decentralized online convex optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6887425)