A flexible gradient tracking algorithmic framework for decentralized optimization

DOI10.1007/S10589-025-00685-WMaRDI QIDQ6961464zbMATH OpenFDO

Authors Albert S. Berahas, Raghu Bollapragada, Shagun Gupta

Publication date 10 July 2025

Published in Computational Optimization and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10589-025-00685-W

zbMATH Keywords

communicationcomputationdecentralized optimizationgradient tracking methodsrandomized

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Deterministic network models in operations research (90B10) Large-scale problems in mathematical programming (90C06) Convex programming (90C25)

Cites work

• Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
• Adaptive consensus: a network pruning approach for decentralized optimization
• Balancing Communication and Computation in Distributed Optimization
• Balancing communication and computation in gradient tracking algorithms for decentralized optimization
• Consensus-based distributed support vector machines
• Distributed Optimization Based on Gradient Tracking Revisited: Enhancing Convergence Rate via Surrogation
• Distributed Spectrum Sensing for Cognitive Radio Networks by Exploiting Sparsity
• Distributed stochastic gradient tracking methods
• EXTRA: an exact first-order algorithm for decentralized consensus optimization
• FedPD: a federated learning framework with adaptivity to non-IID data
• FlexPD: A Flexible Framework of First-Order Primal-Dual Algorithms for Distributed Optimization
• Harnessing Smoothness to Accelerate Distributed Optimization
• scientific article; zbMATH DE number 6508162 (Why is no real title available?)
• Local exact-diffusion for decentralized optimization and learning
• Network Newton Distributed Optimization Methods
• On the Convergence of Nested Decentralized Gradient Methods With Multiple Consensus and Gradient Steps
• Proximal splitting methods in signal processing
• Push–Pull Gradient Methods for Distributed Optimization in Networks

This page was built for publication: A flexible gradient tracking algorithmic framework for decentralized optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6961464)