Distributed Optimization Over Dependent Random Networks
From MaRDI portal
Abstract: We study the averaging-based distributed optimization solvers over random networks. We show a general result on the convergence of such schemes using weight-matrices that are row-stochastic almost surely and column-stochastic in expectation for a broad class of dependent weight-matrix sequences. In addition to implying many of the previously known results on this domain, our work shows the robustness of distributed optimization results to link-failure. Also, it provides a new tool for synthesizing distributed optimization algorithms. {To prove our main theorem, we establish new results on the rate of convergence analysis of averaging dynamics over (dependent) random networks. These secondary results, along with the required martingale-type results to establish them, might be of interest to broader research endeavors in distributed computation over random networks.
Cited in
(8)- Distributed stochastic algorithm for global optimization in networked system
- Distributed resource allocation over random networks based on stochastic approximation
- ADVANCES IN DISTRIBUTED OPTIMIZATION USING PROBABILITY COLLECTIVES
- scientific article; zbMATH DE number 5283386 (Why is no real title available?)
- Distributed Inference Over Directed Networks: Performance Limits and Optimal Design
- Distributed Multiagent Convex Optimization Over Random Digraphs
- Distributed learning for random vector functional-link networks
- Almost sure convergence of distributed optimization with imperfect information sharing
This page was built for publication: Distributed Optimization Over Dependent Random Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6093203)