Truncated stochastic approximation with moving bounds: convergence
From MaRDI portal
Publication:398576
Abstract: In this paper we propose a wide class of truncated stochastic approximation procedures with moving random bounds. While we believe that the proposed class of procedures will find its way to a wider range of applications, the main motivation is to accommodate applications to parametric statistical estimation theory. Our class of stochastic approximation procedures has three main characteristics: truncations with random moving bounds, a matrix valued random step-size sequence, and dynamically changing random regression function. We establish convergence and consider several examples to illustrate the results.
Recommendations
- Rate of convergence of truncated stochastic approximation procedures with moving bounds
- Asymptotic behavior of truncated stochastic approximation procedures
- scientific article; zbMATH DE number 3992716
- scientific article; zbMATH DE number 4107968
- Asymptotic normality of randomly truncated stochastic algorithms
Cites work
- A Stochastic Approximation Algorithm with Varying Bounds
- A Stochastic Approximation Method
- Almost sure convergence of randomly truncated stochastic algorithms under verifiable condi\-tions
- Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
- Efficient on-line estimation of autoregressive parameters
- Efficient recursive estimation. Application to estimating the parameters of a covariance function
- Foundations of Modern Probability
- scientific article; zbMATH DE number 3852087 (Why is no real title available?)
- scientific article; zbMATH DE number 3875113 (Why is no real title available?)
- scientific article; zbMATH DE number 5348356 (Why is no real title available?)
- scientific article; zbMATH DE number 48727 (Why is no real title available?)
- scientific article; zbMATH DE number 1210653 (Why is no real title available?)
- scientific article; zbMATH DE number 1972910 (Why is no real title available?)
- scientific article; zbMATH DE number 3992716 (Why is no real title available?)
- scientific article; zbMATH DE number 3449561 (Why is no real title available?)
- scientific article; zbMATH DE number 3103824 (Why is no real title available?)
- On asymptotically efficient recursive estimation
- On the recursive parameter estimation in the general discrete time statistical model
- Rate of Convergence in Recursive Parameter Estimation procedures
- Recursive computation of M-estimates for the parameters of a finite autoregressive process
- Recursive estimators for stationary, strong mixing processes - a representation theorem and asymptotic distributions
- Recursive parameter estimation: asymptotic expansion
- Recursive parameter estimation: convergence
- Robust identification
- Semimartingale stochastic approximation procedure and recursive estimation
- Stability of Stochastic Approximation under Verifiable Conditions
- Stochastic approximation
- Stochastic approximation with random truncations, state-dependent noise and discontinuous dynamics
- Stochastic gradient algorithm with random truncations
Cited in
(13)- Convergence analysis of dynamic stochastic approximation
- Asymptotic behavior of truncated stochastic approximation procedures
- Penalty-regulated dynamics and robust learning procedures in games
- scientific article; zbMATH DE number 3934325 (Why is no real title available?)
- scientific article; zbMATH DE number 3942843 (Why is no real title available?)
- scientific article; zbMATH DE number 4028679 (Why is no real title available?)
- scientific article; zbMATH DE number 4107968 (Why is no real title available?)
- scientific article; zbMATH DE number 3992716 (Why is no real title available?)
- Rate of convergence of truncated stochastic approximation procedures with moving bounds
- A new recursive estimation method for single input single output models
- scientific article; zbMATH DE number 6253875 (Why is no real title available?)
- Asymptotic normality of randomly truncated stochastic algorithms
- Almost sure convergence of randomly truncated stochastic algorithms under verifiable condi\-tions
This page was built for publication: Truncated stochastic approximation with moving bounds: convergence
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q398576)