Performance of a Distributed Stochastic Approximation Algorithm
From MaRDI portal
Abstract: In this paper, a distributed stochastic approximation algorithm is studied. Applications of such algorithms include decentralized estimation, optimization, control or computing. The algorithm consists in two steps: a local step, where each node in a network updates a local estimate using a stochastic approximation algorithm with decreasing step size, and a gossip step, where a node computes a local weighted average between its estimates and those of its neighbors. Convergence of the estimates toward a consensus is established under weak assumptions. The approach relies on two main ingredients: the existence of a Lyapunov function for the mean field in the agreement subspace, and a contraction property of the random matrices of weights in the subspace orthogonal to the agreement subspace. A second order analysis of the algorithm is also performed under the form of a Central Limit Theorem. The Polyak-averaged version of the algorithm is also considered.
Cited in
(20)- Stochastic analysis of average-based distributed algorithms
- Empirical measure large deviations for reinforced chains on finite spaces
- On the rates of convergence of parallelized averaged stochastic gradient algorithms
- Stochastic Algorithms: Foundations and Applications
- Large deviations analysis for distributed algorithms in an ergodic Markovian environment
- Multi-agent natural actor-critic reinforcement learning algorithms
- Time averaging algorithms with stopping rules for multi-agent consensus with noisy measurements
- A distributed stochastic approximation algorithm for stochastic LQ control with unknown uncertainty
- Decentralized control for optimal LQ problems in stochastic systems with unknown uncertainties
- Distributed stochastic compositional optimization problems over directed networks
- On the Divergence of Decentralized Nonconvex Optimization
- Central limit theorems for stochastic approximation with controlled Markov chain dynamics
- Asymptotic properties of dual averaging algorithm for constrained distributed stochastic optimization
- Nonlinear gossip
- Consensus-based decentralized real-time identification of large-scale systems
- Distributed estimation with quantized measurements and communication over Markovian switching topologies
- An event-triggering algorithm for decentralized stochastic optimization over networks
- Confidence region for distributed stochastic optimization problem via stochastic gradient tracking method
- Finite-time error bounds for distributed linear stochastic approximation
- Stochastic learning in multi-agent optimization: communication and payoff-based approaches
This page was built for publication: Performance of a Distributed Stochastic Approximation Algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5346264)
