Compressed gradient tracking algorithms for distributed nonconvex optimization

DOI10.1016/J.AUTOMATICA.2025.112286MaRDI QIDQ6980069zbMATH OpenFDO

Authors Xinlei Yi, Guanghui Wen, Yang Shi, Karl Henrik Johansson, Tao Yang, Lei Xu

Publication date 23 May 2025

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AUTOMATICA.2025.112286

zbMATH Keywords

communication compressiongradient tracking algorithmlinear convergencenonconvex optimizationPolyak-Łojasiewicz conditionsublinear convergence

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26)

Cites work

• A Compressed Gradient Tracking Method for Decentralized Optimization With Linear Convergence
• Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
• Adaptation, learning, and optimization over networks
• An Improved Convergence Analysis for Decentralized Online Stochastic Non-Convex Optimization
• Communication Compression for Distributed Nonconvex Optimization
• Compressed Gradient Methods With Hessian-Aided Error Compensation
• Convergence of Asynchronous Distributed Gradient Methods Over Stochastic Networks
• Convergence Rates of Distributed Gradient Methods Under Random Quantization: A Stochastic Approximation Approach
• Distributed convex optimization via continuous-time coordination algorithms with discrete-time communication
• Distributed Discrete-Time Optimization in Multiagent Networks Using Only Sign of Relative State
• Distributed dual averaging method for multi-agent optimization with quantized communication
• Distributed gradient tracking methods with finite data rates
• Distributed Subgradient Methods for Multi-Agent Optimization
• Distributed Zero-Order Algorithms for Nonconvex Multiagent Optimization
• EXTRA: an exact first-order algorithm for decentralized consensus optimization
• Harnessing Smoothness to Accelerate Distributed Optimization
• Innovation Compression for Communication-Efficient Distributed Optimization With Linear Convergence
• Linear Convergence of First- and Zeroth-Order Primal–Dual Algorithms for Distributed Nonconvex Optimization
• Linear convergence of primal-dual gradient methods and their performance in distributed optimization
• Newton-Raphson Consensus for Distributed Convex Optimization
• Quantized Distributed Gradient Tracking Algorithm With Linear Convergence in Directed Networks
• Quantized Subgradient Algorithm and Data-Rate Analysis for Distributed Optimization
• Sensor Network Event Localization via Nonconvex Nonsmooth ADMM and Augmented Lagrangian Methods
• Stochastic distributed learning with gradient quantization and double-variance reduction
• The Gradient Tracking Is a Distributed Integral Action

This page was built for publication: Compressed gradient tracking algorithms for distributed nonconvex optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6980069)