Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning

DOI10.1002/rnc.5151zbMath1525.93431OpenAlexW3088171231MaRDI QIDQ6054830

Jingyi Zhu, James C. Spall

Publication date: 25 October 2023

Published in: International Journal of Robust and Nonlinear Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/rnc.5151

zbMATH Keywords

trackingtime-varying systemsstochastic approximationstochastic gradient descentsimultaneous perturbation stochastic approximationnondecaying gain

Mathematics Subject Classification ID

Adaptive control/observation systems (93C40) Stochastic systems in control theory (general) (93E03)

Related Items (3)

An iteratively regularized stochastic gradient method for estimating a random parameter in a stochastic PDE. A variational inequality approach ⋮ Unnamed Item ⋮ A regularized stochastic subgradient projection method for an optimal control problem in a stochastic partial differential equation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A solution to the multivariate behrens-fisher problem
• The Welch-James approximation to the distribution of the residual sum of squares in a weighted linear regression
• A one-measurement form of simultaneous perturbation stochastic approximation
• Adaptation and tracking in system identification - a survey
• Tracking error bounds of adaptive nonstationary filtering
• Multivariate generalizations of the Wald-Wolfowitz and Smirnov two-sample tests
• Stochastic approximation methods for constrained and unconstrained systems
• Modified Nel and van der Merwe test for the multivariate Behrens-Fisher problem.
• Online natural gradient as a Kalman filter
• Uncertainties for recursive estimators in nonlinear state-space models, with applications to epidemiology
• Gradient methods for nonstationary unconstrained optimization problems
• Adaptive stochastic approximation by the simultaneous perturbation method
• Non-Stationary Stochastic Optimization
• Tracking properties of adaptive signal processing algorithms
• Identification of linear parameter varying models
• Accelerated Stochastic Approximation
• Frequency domain tracking characteristics of adaptive algorithms
• Estimating time-varying parameters by the Kalman filter based algorithm: stability and convergence
• Stochastic Minimization with Constant Step-Size: Asymptotic Laws
• Optimization of adaptive identification for time-varying filters
• Asymptotic Properties of Stochastic Approximations with Constant Coefficients
• A result on the mean square error obtained using general tracking algorithms
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• An invariance principle for the Robbins-Monro process in a Hilbert space
• On positive real transfer functions and the convergence of some recursive schemes
• Analysis of recursive stochastic algorithms
• Introduction to Stochastic Search and Optimization
• Adaptive Sequential Stochastic Optimization
• Asymptotical Study of Parameter Tracking Algorithms
• Performance analysis of general tracking algorithms
• Analysis of adaptive step-size SA algorithms for parameter tracking
• Feedback and Weighting Mechanisms for Improving Jacobian Estimates in the Adaptive Simultaneous Perturbation Algorithm
• Option pricing when underlying stock returns are discontinuous
• A combination of Wilcoxon's and Ansari-Bradley's statistics
• A Stochastic Approximation Method
• Approximation Methods which Converge with Probability one
• Stochastic approximation algorithms: overview and recent trends.

This page was built for publication: Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning