Stochastic Minimization with Constant Step-Size: Asymptotic Laws

DOI10.1137/0324039MaRDI QIDQ3725895zbMATH OpenOpenAlexFDO

Authors 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 distributionconstant step-size constant gainconstrained stochastic approximation processMarkovian processstationary distribution

Mathematics Subject Classification ID

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

Recommendations

• Rate of Convergence for Constrained Stochastic Approximation Algorithms
• scientific article; zbMATH DE number 3896700
• scientific article; zbMATH DE number 4113792
• Asymptotic Behavior of a Markovian Stochastic Algorithm with Constant Step
• scientific article; zbMATH DE number 3926029

Cited in

(15)

• Asymptotic behavior of constrained stochastic approximations via the theory of large deviations
• Stochastic approximation algorithms with constant step size whose average is cooperative
• Sampling from a log-concave distribution with projected Langevin Monte Carlo
• Estimation of an optimal solution of a LP problem with unknown objective function
• Bridging the gap between constant step size stochastic gradient descent and Markov chains
• Non-asymptotic error bounds for constant stepsize stochastic approximation for tracking mobile agents
• Asymptotic Behavior of a Markovian Stochastic Algorithm with Constant Step
• Constant step stochastic approximations involving differential inclusions: stability, long-run convergence and applications
• A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares)
• Stochastic algorithms for the estimation of an optimal solution of a LP problem. Convergence and central limit theorem
• Stochastic approximation algorithms: overview and recent trends.
• Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning
• scientific article; zbMATH DE number 7733450 (Why is no real title available?)
• Convergence and concentration properties of constant step-size SGD through Markov chains
• Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3725895)