A stochastic averaging gradient algorithm with multi‐step communication for distributed optimization

DOI10.1002/oca.2973MaRDI QIDQ6054701

Zheng Wang, Zhenyuan Du, Jinhui Hu, Unnamed Author, Huaqing Li, Yu Yan, Liping Feng

Publication date: 25 October 2023

Published in: Optimal Control Applications and Methods (Search for Journal in Brave)

zbMATH Keywords

distributed convex optimizationlinear convergence ratestochastic averaging gradientmulti-step communication

Mathematics Subject Classification ID

Convex programming (90C25) Optimal stochastic control (93E20) Networked control (93B70)

Cites Work

• Unnamed Item
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• Minimizing finite sums with the stochastic average gradient
• Distributed stochastic subgradient projection algorithms for convex optimization
• Optimal distributed stochastic mirror descent for strongly convex optimization
• DSA: Decentralized Double Stochastic Averaging Gradient Algorithm
• Excess-Risk of Distributed Stochastic Learners
• Stochastic Gradient-Push for Strongly Convex Functions on Time-Varying Directed Graphs
• Noise Reduction by Swarming in Social Foraging
• Explicit Convergence Rate of a Distributed Alternating Direction Method of Multipliers
• Fast Distributed Gradient Methods
• Approximate Projection Methods for Decentralized Optimization With Functional Constraints
• Linear Convergence in Optimization Over Directed Graphs With Row-Stochastic Matrices
• On Projected Stochastic Gradient Descent Algorithm with Weighted Averaging for Least Squares Regression
• Fast Convergence Rates for Distributed Non-Bayesian Learning
• Diffusion Adaptation Strategies for Distributed Optimization and Learning Over Networks
• On the Linear Convergence of the ADMM in Decentralized Consensus Optimization
• Hybrid Random/Deterministic Parallel Algorithms for Convex and Nonconvex Big Data Optimization
• Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
• Harnessing Smoothness to Accelerate Distributed Optimization
• Robust Asynchronous Stochastic Gradient-Push: Asymptotically Optimal and Network-Independent Performance for Strongly Convex Functions
• Distributed Subgradient Methods for Multi-Agent Optimization
• Fast Decentralized Nonconvex Finite-Sum Optimization with Recursive Variance Reduction
• FlexPD: A Flexible Framework of First-Order Primal-Dual Algorithms for Distributed Optimization
• EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
• Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
• ADD-OPT: Accelerated Distributed Directed Optimization

This page was built for publication: A stochastic averaging gradient algorithm with multi‐step communication for distributed optimization