One-sided convergence of the Robbins-Monro process
From MaRDI portal
A modified Robbins-Monro process is considered for estimation of roots of regression functions. It is shown that the iterative process converges to the root with probability one and that the estimates exceed the root only by a finite number of times with probability one. The result has been established by the author previously [ibid. 41, 1682-1684 (1981); translation from Avtom. Telemekh. 1980, No.12, 72-75 (1980; Zbl 0464.62081)] but under more stringent assumptions.
Recommendations
Cited in
(13)- Estimating conditional quantiles at the root of a regression function
- On one-sided convergence of a modified stochastic approximation process
- A probability estimate for not exceeding the unknown threshold by the Robbins-Monro algorithm
- scientific article; zbMATH DE number 4133352 (Why is no real title available?)
- An estimate for the rate of convergence of the Robbins-Monro process
- Convergence of a Robbins-Monro Algorithm for Recursive Estimation with Non-Monotone Weights for a Function with a Restricted Domain and Multiple Zeros
- General non-asymptotic estimates of the rate of convergence of iterative stochastic algorithms
- scientific article; zbMATH DE number 4055175 (Why is no real title available?)
- scientific article; zbMATH DE number 4109895 (Why is no real title available?)
- scientific article; zbMATH DE number 124608 (Why is no real title available?)
- scientific article; zbMATH DE number 4113051 (Why is no real title available?)
- scientific article; zbMATH DE number 4186924 (Why is no real title available?)
- Necessary and sufficient conditions for the Robbins-Monro method
This page was built for publication: One-sided convergence of the Robbins-Monro process
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1098528)
