Approximate dual averaging method for multiagent saddle-point problems with stochastic subgradients

DOI10.1155/2014/202737MaRDI QIDQ1717855zbMATH OpenOpenAlexWikidataFDO

Authors Deming Yuan, Yang Yang

Publication date 8 February 2019

Published in Mathematical Problems in Engineering (Search for Journal in Brave)

Copyright license Creative Commons Attribution 3.0 Unported

Full work available at URL https://doi.org/10.1155/2014/202737

Mathematics Subject Classification ID

Communication networks in operations research (90B18) Stochastic programming (90C15) Convex programming (90C25) Programming involving graphs or networks (90C35) Minimax problems in mathematical programming (90C47)

Review text

Summary: This paper considers the problem of solving the saddle-point problem over a network, which consists of multiple interacting agents. The global objective function of the problem is a combination of local convex-concave functions, each of which is only available to one agent. Our main focus is on the case where the projection steps are calculated approximately and the subgradients are corrupted by some stochastic noises. We propose an approximate version of the standard dual averaging method and show that the standard convergence rate is preserved, provided that the projection errors decrease at some appropriate rate and the noises are zero-mean and have bounded variance.

Recommendations

• Inexact dual averaging method for distributed multi-agent optimization
• Distributed stochastic subgradient projection algorithms for convex optimization
• Stochastic mirror descent method for distributed multi-agent optimization
• Distributed primal-dual stochastic subgradient algorithms for multi-agent optimization under inequality constraints
• Primal-dual stochastic distributed algorithm for constrained convex optimization

Cites work

• Consensus Problems in Networks of Agents With Switching Topology and Time-Delays
• Consensus seeking in multiagent systems under dynamically changing interaction topologies
• Cooperative distributed multi-agent optimization
• Coordination of groups of mobile autonomous agents using nearest neighbor rules
• Distributed Containment Control with Multiple Dynamic Leaders for Double-Integrator Dynamics Using Only Position Measurements
• Distributed discrete-time coordinated tracking with Markovian switching topologies
• Distributed dual averaging method for multi-agent optimization with quantized communication
• Distributed Subgradient Methods for Multi-Agent Optimization
• Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
• Fast linear iterations for distributed averaging
• Gossip Algorithms for Convex Consensus Optimization Over Networks
• Gradient‐free method for distributed multi‐agent optimization via push‐sum algorithms
• scientific article; zbMATH DE number 5454133 (Why is no real title available?)
• On Distributed Convex Optimization Under Inequality and Equality Constraints
• Primal-dual subgradient methods for convex problems
• Subgradient methods for saddle-point problems

This page was built for publication: Approximate dual averaging method for multiagent saddle-point problems with stochastic subgradients

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1717855)