Rate of convergence of truncated stochastic approximation procedures with moving bounds

DOI10.3103/S1066530716040025zbMATH Open1362.62050arXiv1508.01902OpenAlexW2553910665MaRDI QIDQ523725FDOQ523725

Authors: Yong-Cai Geng, Sumit K. Garg 

Publication date: 21 April 2017

Published in: Mathematical Methods of Statistics (Search for Journal in Brave)

Abstract: The paper is concerned with stochastic approximation procedures having three main characteristics: truncations with random moving bounds, a matrix valued random step-size sequence, and a dynamically changing random regression function. We study convergence and rate of convergence. Main results are supplemented with corollaries to establish various sets of sufficient conditions, with the main emphases on the parametric statistical estimation. The theory is illustrated by examples and special cases.

Full work available at URL: https://arxiv.org/abs/1508.01902

Recommendations

• Truncated stochastic approximation with moving bounds: convergence
• 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

zbMATH Keywords

parameter estimationrecursive estimationstochastic approximation

Mathematics Subject Classification ID

Point estimation (62F10) Asymptotic properties of parametric estimators (62F12) Robustness and adaptive procedures (parametric inference) (62F35) Stochastic approximation (62L20)

Cites Work

• Matrix Analysis
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Stochastic Approximation Method
• Efficient on-line estimation of autoregressive parameters
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Stochastic Approximation Algorithm with Varying Bounds
• Stochastic approximation
• Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
• Robust identification
• Recursive computation of M-estimates for the parameters of a finite autoregressive process
• On asymptotically efficient recursive estimation
• Stochastic gradient algorithm with random truncations
• On the recursive parameter estimation in the general discrete time statistical model
• Semimartingale stochastic approximation procedure and recursive estimation
• Efficient recursive estimation. Application to estimating the parameters of a covariance function
• Truncated stochastic approximation with moving bounds: convergence
• Title not available (Why is that?)
• Stochastic approximation with random truncations, state-dependent noise and discontinuous dynamics
• Rate of Convergence in Recursive Parameter Estimation procedures
• Recursive parameter estimation: convergence
• Recursive parameter estimation: asymptotic expansion
• Recursive estimators for stationary, strong mixing processes - a representation theorem and asymptotic distributions
• Almost sure convergence of randomly truncated stochastic algorithms under verifiable condi\-tions
• The robbins-monro type stochastic differential equations. I. convergence of solutions

Cited In (4)

• Truncated stochastic approximation with moving bounds: convergence
• Asymptotic behavior of truncated stochastic approximation procedures
• Asymptotic normality of randomly truncated stochastic algorithms
• Title not available (Why is that?)

This page was built for publication: Rate of convergence of truncated stochastic approximation procedures with moving bounds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q523725)