Performance analysis of stochastic gradient algorithms under weak conditions

DOI10.1007/s11432-008-0117-yzbMath1145.93050OpenAlexW2054463619MaRDI QIDQ948509

Feng Ding, Fei Liu, Hui-Zhong Yang

Publication date: 16 October 2008

Published in: Science in China. Series F (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11432-008-0117-y

zbMATH Keywords

recursive identificationparameter estimationmultivariable systemsleast squaresconvergence propertiesmartingale convergence theoremstochastic gradient

Mathematics Subject Classification ID

Estimation and detection in stochastic control theory (93E10) Identification in stochastic control theory (93E12)

Related Items

Identification methods for two-variable difference systems, Two-stage least squares based iterative estimation algorithm for CARARMA system modeling, Hierarchical least squares algorithms for single-input multiple-output systems based on the auxiliary model, Two-stage recursive least squares parameter estimation algorithm for output error models, Least squares parameter estimation and multi-innovation least squares methods for linear fitting problems from noisy data, Separable synthesis gradient estimation methods and convergence analysis for multivariable systems, Auxiliary model based multi-innovation algorithms for multivariable nonlinear systems, Distributed online multi‐task sparse identification for multiple systems with asynchronous updates, Performance analysis of the AM-SG parameter estimation for multivariable systems, Maximum likelihood interval-varying recursive least squares identification for output-error autoregressive systems with scarce measurements, Filtering-based gradient joint identification algorithms for nonlinear fractional-order models with colored noises, Hierarchical least squares based iterative estimation algorithm for multivariable Box-Jenkins-like systems using the auxiliary model, Parameter and order estimation algorithms and convergence analysis for lithium‐ion batteries, Iterative estimation methods for Hammerstein controlled autoregressive moving average systems based on the key-term separation principle, Gradient-based parameter estimation for input nonlinear systems with ARMA noises based on the auxiliary model, Two-stage least squares based iterative identification algorithm for controlled autoregressive moving average (CARMA) systems, Multi-innovation extended stochastic gradient algorithm and its performance analysis, The innovation algorithms for multivariable state‐space models, Two identification methods for dual-rate sampled-data nonlinear output-error systems, Recursive least-squares estimation for Hammerstein nonlinear systems with nonuniform sampling, Recursive identification of time-varying systems: self-tuning and matrix RLS algorithms, Consistency of the extended gradient identification algorithm for multi-input multi-output systems with moving average noises, Gradient based iterative solutions for general linear matrix equations, The residual based interactive least squares algorithms and simulation studies, Parameter identification of systems with preload nonlinearities based on the finite impulse response model and negative gradient search, An iterative least squares estimation algorithm for controlled moving average systems based on matrix decomposition, Time series AR modeling with missing observations based on the polynomial transformation, Convergence of stochastic gradient estimation algorithm for multivariable ARX-like systems, Iterative identification algorithm for Wiener nonlinear systems using the Newton method, Gradient based iterative parameter identification for Wiener nonlinear systems, On-line parameter estimation for a class of time-varying continuous systems with bounded disturbances, The residual based interactive stochastic gradient algorithms for controlled moving average models, Multi-innovation stochastic gradient algorithm for multiple-input single-output systems using the auxiliary model, The data filtering based generalized stochastic gradient parameter estimation algorithms for multivariate output-error autoregressive systems using the auxiliary model, Gradient-based iterative identification for MISO Wiener nonlinear systems: application to a glutamate fermentation process

Cites Work

• Unnamed Item
• Unnamed Item
• Combined parameter and output estimation of dual-rate systems using an auxiliary model
• Performance analysis of multi-innovation gradient type identification methods
• Auxiliary model-based least-squares identification methods for Hammerstein output-error systems
• Adaptive prediction by least squares predictors in stochastic regression models with applications to time series
• Identification and stochastic adaptive control
• Identification of Hammerstein nonlinear ARMAX systems
• Extended least squares and their applications to adaptive control and prediction in linear systems
• The convergence of AML
• Recursive Identification and Adaptive Prediction in Linear Stochastic Systems
• Consistency of the least-squares identification method
• On the convergence of least squares estimates in white noise
• Stochastic adaptive prediction and model reference control
• Performance bounds of forgetting factor least-squares algorithms for time-varying systems with finite measurement data
• Least squares based self‐tuning control of dual‐rate systems
• Hierarchical least squares identification methods for multivariable systems
• Parameter estimation of dual-rate stochastic systems by using an output error method
• Adaptive Digital Control of Hammerstein Nonlinear Systems with Limited Output Sampling
• Least squares estimates in stochastic regression models with applications to identification and control of dynamic systems