Distributed Stochastic Approximation: Weak Convergence and Network Design
From MaRDI portal
Abstract: This paper studies distributed stochastic approximation algorithms based on broadcast gossip on communication networks represented by digraphs. Weak convergence of these algorithms is proved, and an associated ordinary differential equation (ODE) is formulated connecting convergence points with local objective functions and network properties. Using these results, a methodology is proposed for network design, aimed at achieving the desired asymptotic behavior at consensus. Convergence rate of the algorithm is also analyzed and further improved using an attached stochastic differential equation. Simulation results illustrate the theoretical concepts.
Cited in
(11)- Push–Pull Gradient Methods for Distributed Optimization in Networks
- scientific article; zbMATH DE number 175782 (Why is no real title available?)
- Distributed consensus-based multi-agent temporal-difference learning
- Distributed Inference Over Directed Networks: Performance Limits and Optimal Design
- Distributed stochastic algorithm for global optimization in networked system
- Distributed web hacking by adaptive consensus-based reinforcement learning
- Multi-agent off-policy actor-critic algorithm for distributed multi-task reinforcement learning
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- Dense limit of the Dawid–Skene model for crowdsourcing and regions of sub-optimality of message passing algorithms
- Nonlinear robustified stochastic consensus seeking
- Finite-time error bounds for distributed linear stochastic approximation
This page was built for publication: Distributed Stochastic Approximation: Weak Convergence and Network Design
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2979357)
