Analysis of adaptive step-size SA algorithms for parameter tracking

DOI10.1109/9.402231MaRDI QIDQ4850483zbMATH OpenOpenAlexFDO

Authors Harold J. Kushner, Jichuan Yang

Publication date 23 June 1996

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/9.402231

zbMATH Keywords

adaptive stochastic approximation algorithmsstep-size

Mathematics Subject Classification ID

Estimation and detection in stochastic control theory (93E10) Stochastic learning and adaptive control (93E35)

Recommendations

• Adaptive stochastic approximation algorithm
• Adaptive stepsize selection for tracking in a regime-switching environment
• Rates of convergence of adaptive step-size of stochastic approximation algorithms
• Stabilization of stochastic approximation by step size adaptation

Cited in

(20)

• Convergence analysis of batch gradient algorithm for three classes of sigma-pi neural networks
• Tracking randomly varying parameters: Analysis of a standard algorithm
• Adaptive stochastic approximation algorithm
• Cyclic stochastic approximation with disturbance on input in the parameter tracking problem based on a multiagent algorithm
• An algorithm for blind equalization and synchronization
• Low-complexity adaptive step size constrained constant modulus SG algorithms for adaptive beamforming
• Adaptive step size selection in distributed optimization with observation noise and unknown stochastic target variation
• Random belief system dynamics in complex networks under time-varying logic constraints
• Optimal stochastic extragradient schemes for pseudomonotone stochastic variational inequality problems and their variants
• Adaptive stepsize selection for tracking in a regime-switching environment
• Persistent tracking and identification of regime-switching systems with structural uncertainties: unmodeled dynamics, observation bias, and nonlinear model mismatch
• scientific article; zbMATH DE number 3919771 (Why is no real title available?)
• System identification: regime switching, unmodeled dynamics, and binary sensors
• Temporally adaptive estimation of logistic classifiers on data streams
• Online linear and quadratic discriminant analysis with adaptive forgetting for streaming classification
• Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning
• Change-point monitoring for online stochastic approximations
• Implicit score-driven filters for time-varying parameter models
• Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming
• Sequential reconstruction of driving-forces from nonlinear nonstationary dynamics

This page was built for publication: Analysis of adaptive step-size SA algorithms for parameter tracking

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4850483)