Stochastic Minimization with Constant Step-Size: Asymptotic Laws

DOI10.1137/0324039zbMath0594.90089OpenAlexW1991238514MaRDI QIDQ3725895

Georg Ch. Pflug

Publication date: 1986

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/0324039

zbMATH Keywords

asymptotic distributionstationary distributionMarkovian processconstant step-size constant gainconstrained stochastic approximation process

Mathematics Subject Classification ID

Stochastic programming (90C15) Markov and semi-Markov decision processes (90C40)

Related Items (10)

Asymptotic behavior of constrained stochastic approximations via the theory of large deviations ⋮ Sampling from a log-concave distribution with projected Langevin Monte Carlo ⋮ Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning ⋮ Bridging the gap between constant step size stochastic gradient descent and Markov chains ⋮ Unnamed Item ⋮ Estimation of an optimal solution of a LP problem with unknown objective function ⋮ Stochastic approximation algorithms: overview and recent trends. ⋮ Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size ⋮ Stochastic Algorithms for the Estimation of an Optimal Solution of a LP Problem. Convergence and Central Limit Theorem ⋮ Non-asymptotic error bounds for constant stepsize stochastic approximation for tracking mobile agents

This page was built for publication: Stochastic Minimization with Constant Step-Size: Asymptotic Laws