Improving the convergence of distributed gradient descent via inexact average consensus

DOI10.1007/S10957-020-01648-3MaRDI QIDQ2178889zbMATH OpenOpenAlexFDO

Authors Bin Du, Jiazhen Zhou, Dengfeng Sun

Publication date 11 May 2020

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

Full work available at URL https://doi.org/10.1007/s10957-020-01648-3

zbMATH Keywords

average consensusdistributed gradient descentdistributed optimizationinexact convergence

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Convex programming (90C25) Programming involving graphs or networks (90C35)

Recommendations

• Inexact dual averaging method for distributed multi-agent optimization
• On the convergence of decentralized gradient descent
• On the convergence of exact distributed generalisation and acceleration algorithm for convex optimisation
• Distributed consensus-based multi-agent convex optimization via gradient tracking technique
• EXTRA: an exact first-order algorithm for decentralized consensus optimization

Cites work

• Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
• Balancing Communication and Computation in Distributed Optimization
• Consensus in Ad Hoc WSNs With Noisy Links—Part II: Distributed Estimation and Smoothing of Random Signals
• Constrained Consensus and Optimization in Multi-Agent Networks
• Distributed control of robotic networks: a mathematical approach to motion coordination algorithms.
• Distributed Spectrum Sensing for Cognitive Radio Networks by Exploiting Sparsity
• Distributed Stopping for Average Consensus in Digraphs
• Distributed stopping for average consensus in undirected graphs via event-triggered strategies
• Distributed Subgradient Methods for Multi-Agent Optimization
• EXTRA: an exact first-order algorithm for decentralized consensus optimization
• Fast Distributed Gradient Methods
• On the Linear Convergence of the ADMM in Decentralized Consensus Optimization

Cited in

(4)

• Privacy-preserving dual stochastic push-sum algorithm for distributed constrained optimization
• Distributed optimization with inexact oracle
• S-NEAR-DGD: A Flexible Distributed Stochastic Gradient Method for Inexact Communication
• Decentralized online strongly convex optimization with general compressors and random disturbances

This page was built for publication: Improving the convergence of distributed gradient descent via inexact average consensus

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2178889)