Balancing communication and computation in gradient tracking algorithms for decentralized optimization

DOI10.1007/S10957-024-02554-8MaRDI QIDQ6655816zbMATH OpenFDO

Authors Albert S. Berahas, Raghu Bollapragada, Shagun Gupta

Publication date 27 December 2024

Published in Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10957-024-02554-8

zbMATH Keywords

communicationcomputationdecentralized optimizationgradient tracking methodsnetwork optimization

Mathematics Subject Classification ID

Numerical methods based on nonlinear programming (49M37) Numerical mathematical programming methods (65K05) Large-scale problems in mathematical programming (90C06) Convex programming (90C25) Nonlinear programming (90C30) Programming involving graphs or networks (90C35)

Recommendations

• A decentralized Nesterov gradient method for stochastic optimization over unbalanced directed networks
• Optimal gradient tracking for decentralized optimization
• Distributed stochastic gradient tracking methods
• Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs
• Communication-efficient algorithms for decentralized and stochastic optimization

Cites work

• A fast row-stochastic decentralized method for distributed optimization over directed graphs
• Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
• ADD-OPT: Accelerated Distributed Directed Optimization
• AsySPA: An Exact Asynchronous Algorithm for Convex Optimization Over Digraphs
• Balancing Communication and Computation in Distributed Optimization
• Communication-efficient distributed optimization of self-concordant empirical loss
• Consensus-based distributed support vector machines
• Decentralized Proximal Gradient Algorithms With Linear Convergence Rates
• DEXTRA: A Fast Algorithm for Optimization Over Directed Graphs
• Distributed Algorithms for Composite Optimization: Unified Framework and Convergence Analysis
• Distributed Linearized Alternating Direction Method of Multipliers for Composite Convex Consensus Optimization
• Distributed Optimization Based on Gradient Tracking Revisited: Enhancing Convergence Rate via Surrogation
• Distributed Optimization Over Time-Varying Directed Graphs
• Distributed stochastic gradient tracking methods
• Distributed Subgradient Methods for Multi-Agent Optimization
• DLM: Decentralized Linearized Alternating Direction Method of Multipliers
• EXTRA: an exact first-order algorithm for decentralized consensus optimization
• 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?)
• Linear Convergence Rate of a Class of Distributed Augmented Lagrangian Algorithms
• Network Newton Distributed Optimization Methods
• On the Convergence of Nested Decentralized Gradient Methods With Multiple Consensus and Gradient Steps
• On the Linear Convergence of the ADMM in Decentralized Consensus Optimization
• Proximal splitting methods in signal processing
• Push–Pull Gradient Methods for Distributed Optimization in Networks

Cited in

(4)

• A variance-reduced stochastic gradient tracking algorithm for decentralized optimization with orthogonality constraints
• Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs
• Optimal gradient tracking for decentralized optimization
• A flexible gradient tracking algorithmic framework for decentralized optimization

This page was built for publication: Balancing communication and computation in gradient tracking algorithms for decentralized optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6655816)