Stochastic approximation

DOI10.1214/aos/1051027873zbMath1039.62077OpenAlexW2043382637MaRDI QIDQ5907083

Tze Leung Lai

Publication date: 18 May 2004

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aos/1051027873

zbMATH Keywords

adaptive controlRobbins-Monrostochastic Lyapunov functionsadaptive stochastic approximationKiefer-Wolfowitz schemesrecursive stochastic algorithms

Mathematics Subject Classification ID

Least squares and related methods for stochastic control systems (93E24) Strong limit theorems (60F15) Biographies, obituaries, personalia, bibliographies (01A70) Stochastic approximation (62L20)

Related Items

A Bayesian stochastic approximation method ⋮ Continuum modeling and control of large nonuniform wireless networks via nonlinear partial differential equations ⋮ Asymptotic behavior of truncated stochastic approximation procedures ⋮ Truncated stochastic approximation with moving bounds: convergence ⋮ Convergence of stochastic approximation via martingale and converse Lyapunov methods ⋮ Two-step estimation in linear regressions with adaptive learning ⋮ Online Covariance Matrix Estimation in Stochastic Gradient Descent ⋮ First-Order Newton-Type Estimator for Distributed Estimation and Inference ⋮ Design of computational intelligent procedure for thermal analysis of porous fin model ⋮ ESTIMATING STRUCTURAL PARAMETERS IN REGRESSION MODELS WITH ADAPTIVE LEARNING ⋮ Revisiting consistency of a recursive estimator of mixing distributions ⋮ Determining the height of energy barriers of the cyclohexene molecule using stochastic approximation ⋮ A stochastic contraction mapping theorem ⋮ Asymptotic properties of predictive recursion: robustness and rate of convergence ⋮ Efficient on-line estimation of autoregressive parameters ⋮ Technical Note—Consistency Analysis of Sequential Learning Under Approximate Bayesian Inference ⋮ Stochastic approximation and compound delayed observations with independent random time delay distribution ⋮ General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type ⋮ A variational inequality based stochastic approximation for inverse problems in stochastic partial differential equations ⋮ Unnamed Item ⋮ Rate of convergence of truncated stochastic approximation procedures with moving bounds ⋮ The Robbins-Monro type stochastic differential equations. III. Polyak's averaging ⋮ A two-stage hybrid procedure for estimating an inverse regression function ⋮ Non-Stationary Stochastic Optimization ⋮ Stochastic approximation: from statistical origin to big-data, multidisciplinary applications ⋮ Simulation-based approach to estimation of latent variable models ⋮ Prediction of Output Response Probability of Sound Environment System Using Simplified Model with Stochastic Regression and Fuzzy Inference ⋮ A stochastic gradient type algorithm for closed-loop problems ⋮ On Incomplete Learning and Certainty-Equivalence Control ⋮ A stochastic approximation view of boosting ⋮ A regularized stochastic subgradient projection method for an optimal control problem in a stochastic partial differential equation ⋮ Asymptotically Optimal Nonparametric Empirical Bayes Via Predictive Recursion ⋮ Unnamed Item ⋮ On the almost sure convergence of adaptive allocation procedures

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Strong consistency of least squares estimates in multiple regression II
• Parametric inference for imperfectly observed Gibbsian fields
• Multivariate adaptive stochastic approximation
• Adaptive design and stochastic approximation
• Iterated least squares in multiperiod control
• Strong consistency of least squares estimates in dynamic models
• Convergence of a stochastic approximation version of the EM algorithm
• On self tuning regulators
• Maximum Likelihood Estimation for Spatial Models by Markov Chain Monte Carlo Stochastic Approximation
• Adaptive stochastic approximation by the simultaneous perturbation method
• On a Class of Stochastic Approximation Processes
• Accelerated Stochastic Approximation
• Efficient Sequential Designs With Binary Data
• Extended least squares and their applications to adaptive control and prediction in linear systems
• A stochastic approximation algorithm with Markov chain Monte-Carlo method for incomplete data estimation problems
• Consistency and asymptotic efficiency of slope estimates in stochastic approximation schemes
• Discrete Time Stochastic Adaptive Control
• Indirect stochastic adaptive control: The general delay-colored noise case
• Recursive Stochastic Algorithms for Global Optimization in $\mathbb{R}^d $
• Parallel Recursive Algorithms in Asymptotically Efficient Adaptive Control of Linear Stochastic Systems
• The AAstrom-Wittenmark self-tuning regulator revisited and ELS-based adaptive trackers
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• Analysis of recursive stochastic algorithms
• An analysis of temporal-difference learning with function approximation
• Optimization of Queues Using an Infinitesimal Perturbation Analysis-Based Stochastic Algorithm with General Update Times
• Rates of Convergence for a Class of Global Stochastic Optimization Algorithms
• An Extension of the Robbins-Monro Procedure
• Asymptotic Distribution of Stochastic Approximation Procedures
• Experimental Determination of the Maximum of a Function
• A Method for Obtaining and Analyzing Sensitivity Data
• Stochastic Estimation of the Maximum of a Regression Function
• Some aspects of the sequential design of experiments
• A Stochastic Approximation Method
• Approximation Methods which Converge with Probability one
• On a Stochastic Approximation Method
• Least squares estimates in stochastic regression models with applications to identification and control of dynamic systems