Stochastic approximation algorithms: Nonasymptotic estimation of their convergence rates
Stochastic approximation algorithms are well--known from optimization theory. However, to apply them properly, the convergence properties must be investigated first. It is known (from the literature) that the technique of Lyapunov functions is here very often employed. However, to obtain ``good convergence results (by Lyapunov approaches) some rather strong conditions are usually assumed. The aim of this paper is to investigate the convergence rate without these assumptions. To obtain more general convergence results the authors replace the investigation of mathematical expectations (of the corresponding Lyapunov functions) by direct investigation in the points of parameter estimates. By this approach they try to omit an ``unpleasant assumption on concavity. Moreover, they extend a class of algorithms that can be properly applied. At the end of the paper the authors mention also the fact that the new results can be successfully employed in the case of adaptive dynamic systems.
- scientific article; zbMATH DE number 1918629
- Rates of convergence of adaptive step-size of stochastic approximation algorithms
- On dynamic stochastic approximation
- Asymptotic behavior of stochastic approximation and large deviations
- Stochastic Approximation and Large Deviations: Upper Bounds and <scp>w.p.1</scp> Convergence
- Sufficient and necessary condition for the convergence of stochastic approximation algorithms
- Consistency of stochastic approximation algorithm with quasi-associated random errors
- Asymptotic behavior of stochastic approximation and large deviations
- scientific article; zbMATH DE number 4141936 (Why is no real title available?)
- Convergence of stochastic approximation algorithms under irregular conditions
- On the Almost Sure Rate of Convergence of Linear Stochastic Approximation Algorithms
- scientific article; zbMATH DE number 3968351 (Why is no real title available?)
- On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates
- scientific article; zbMATH DE number 718744 (Why is no real title available?)
- Convergence Rate of Stochastic Approximation Algorithms in the Degenerate Case
- scientific article; zbMATH DE number 1918629 (Why is no real title available?)
- An alternative proof for convergence of stochastic approximation algorithms
- scientific article; zbMATH DE number 1405930 (Why is no real title available?)
- Polyak's method based on the stochastic Lyapunov function for justifying the consistency of estimates produced by a stochastic approximation search algorithm under an unknown-but-bounded noise
- Convergence of stochastic approximation via martingale and converse Lyapunov methods
This page was built for publication: Stochastic approximation algorithms: Nonasymptotic estimation of their convergence rates
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1281080)
