Performance analysis of stochastic gradient algorithms under weak conditions

DOI10.1007/S11432-008-0117-YMaRDI QIDQ948509zbMATH OpenOpenAlexFDO

Authors Feng Ding, Fei Liu, Huizhong 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

parameter estimationleast squaresstochastic gradientmultivariable systemsrecursive identificationconvergence propertiesmartingale convergence theorem

Mathematics Subject Classification ID

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

Recommendations

• scientific article; zbMATH DE number 1322672
• Convergence analysis of gradient descent stochastic algorithms
• Analysis of stochastic gradient algorithms for linear regression problems
• Strong error analysis for stochastic gradient descent optimization algorithms
• Uniform-in-time weak error analysis for stochastic gradient descent algorithms via diffusion approximation
• Analysis of stochastic gradient descent in continuous time
• New Convergence Aspects of Stochastic Gradient Algorithms
• Convergence analysis of smoothed stochastic gradient-type algorithm
• scientific article; zbMATH DE number 1341059

Cites work

• scientific article; zbMATH DE number 4066707 (Why is no real title available?)
• Adaptive Digital Control of Hammerstein Nonlinear Systems with Limited Output Sampling
• Adaptive prediction by least squares predictors in stochastic regression models with applications to time series
• Auxiliary model-based least-squares identification methods for Hammerstein output-error systems
• Combined parameter and output estimation of dual-rate systems using an auxiliary model
• Consistency of the least-squares identification method
• Extended least squares and their applications to adaptive control and prediction in linear systems
• Hierarchical least squares identification methods for multivariable systems
• Identification and stochastic adaptive control
• Identification of Hammerstein nonlinear ARMAX systems
• Least squares based self‐tuning control of dual‐rate systems
• Least squares estimates in stochastic regression models with applications to identification and control of dynamic systems
• On the convergence of least squares estimates in white noise
• Parameter estimation of dual-rate stochastic systems by using an output error method
• Performance analysis of least mean square algorithm for time-varying systems
• Performance analysis of multi-innovation gradient type identification methods
• Performance bounds of forgetting factor least-squares algorithms for time-varying systems with finite measurement data
• Recursive Identification and Adaptive Prediction in Linear Stochastic Systems
• Stochastic adaptive prediction and model reference control
• The convergence of AML

Cited in

(42)

• The residual based interactive least squares algorithms and simulation studies
• On-line parameter estimation for a class of time-varying continuous systems with bounded disturbances
• Auxiliary model based multi-innovation algorithms for multivariable nonlinear systems
• Filtering-based gradient joint identification algorithms for nonlinear fractional-order models with colored noises
• Two-stage least squares based iterative estimation algorithm for CARARMA system modeling
• Least squares parameter estimation and multi-innovation least squares methods for linear fitting problems from noisy data
• Iterative identification algorithm for Wiener nonlinear systems using the Newton method
• Recursive identification of time-varying systems: self-tuning and matrix RLS algorithms
• Modified stochastic gradient identification algorithms with fast convergence rates
• Gradient based iterative solutions for general linear matrix equations
• Multi-innovation stochastic gradient algorithm for multiple-input single-output systems using the auxiliary model
• Hierarchical least squares based iterative estimation algorithm for multivariable Box-Jenkins-like systems using the auxiliary model
• Gradient based iterative parameter identification for Wiener nonlinear systems
• Gradient-based iterative identification for MISO Wiener nonlinear systems: application to a glutamate fermentation process
• Distributed online multi‐task sparse identification for multiple systems with asynchronous updates
• Convergence of stochastic gradient estimation algorithm for multivariable ARX-like systems
• The data filtering based generalized stochastic gradient parameter estimation algorithms for multivariate output-error autoregressive systems using the auxiliary model
• An iterative least squares estimation algorithm for controlled moving average systems based on matrix decomposition
• Distributed identification based partially-coupled recursive generalized extended least squares algorithm for multivariate input-output-error systems with colored noises from observation data
• Analysis of stochastic gradient algorithms for linear regression problems
• Separable synthesis gradient estimation methods and convergence analysis for multivariable systems
• Performance analysis of the AM-SG parameter estimation for multivariable systems
• 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
• Consistency of the extended gradient identification algorithm for multi-input multi-output systems with moving average noises
• Multi-innovation extended stochastic gradient algorithm and its performance analysis
• Parameter and order estimation algorithms and convergence analysis for lithium‐ion batteries
• Identification methods for two-variable difference systems
• Parameter identification of systems with preload nonlinearities based on the finite impulse response model and negative gradient search
• 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
• Recursive least-squares estimation for Hammerstein nonlinear systems with nonuniform sampling
• The innovation algorithms for multivariable state-space models
• Two-stage least squares based iterative identification algorithm for controlled autoregressive moving average (CARMA) systems
• Maximum likelihood interval-varying recursive least squares identification for output-error autoregressive systems with scarce measurements
• scientific article; zbMATH DE number 4012471 (Why is no real title available?)
• The residual based interactive stochastic gradient algorithms for controlled moving average models
• Two identification methods for dual-rate sampled-data nonlinear output-error systems
• Time series AR modeling with missing observations based on the polynomial transformation
• Auxiliary model maximum likelihood gradient-based iterative identification for feedback nonlinear systems
• The residual-based ESG algorithm and its performance analysis
• Sliding window iterative identification for nonlinear closed-loop systems based on the maximum likelihood principle

This page was built for publication: Performance analysis of stochastic gradient algorithms under weak conditions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q948509)