Stochastic approximation methods for constrained and unconstrained systems

zbMath0381.60004MaRDI QIDQ1248264

Dean S. Clark, Harold J. Kushner

Publication date: 1978

Published in: Applied Mathematical Sciences (Search for Journal in Brave)

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Estimation and detection in stochastic control theory (93E10) Stochastic approximation (62L20) Ordinary differential equations and systems with randomness (34F05) Stochastic partial differential equations (aspects of stochastic analysis) (60H15) Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Research exposition (monographs, survey articles) pertaining to probability theory (60-02)

Related Items

A method combining genetic algorithm with simultaneous perturbation stochastic approximation for linearly constrained stochastic optimization problems, Asymptotic behavior of constrained stochastic approximations via the theory of large deviations, Inventory models under uncertainty: An adaptive approach, Stochastic and robust control of nonlinear economic systems, On convergence of the stochastic subgradient method with on-line stepsize rules, Optimal load sharing in soft real-time systems using likelihood ratios, An algorithm with randomly varying truncation for adaptive beam-formers, A constrained optimization perspective on actor-critic algorithms and application to network routing, Stochastic forward-backward splitting for monotone inclusions, On stochastic extremum seeking via adaptive perturbation-demodulation loop, Approximation of the initial reserve for known ruin probabilities, An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method, Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds, Multiscale Q-learning with linear function approximation, A combined direction stochastic approximation algorithm, A combined algorithm for identification and approximation, Online estimation of hazard rate under random censoring, Strong consistency of recursive identification by no use of persistent excitation condition, Minimizing noisy functionals in Hilbert space: An extension of the Kiefer-Wolfowitz procedure, Optimization of discrete variable stochastic systems by computer simulation, Adaptive filters with constraints and correlated non-stationary signals, Convergence properties of ordinal comparison in the simulation of discrete event dynamic systems, Constrained optimization via stochastic approximation with a simultaneous perturbation gradient approximation, Learning in linear models with expectational leads, On the choice of step size in the Robbins-Monro procedure, Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms, Weighted averaging and stochastic approximation, Rates of convergence of ordinal comparison for dependent discrete event dynamic systems, Linear programming with stochastic elements: An on-line approach, Almost sure convergence of Titterington's recursive estimator for mixture models, On a proof of Robbins-Monro algorithm, Randomized urn models revisited using stochastic approximation, A simulation optimization method that considers uncertainty and multiple performance measures, Convergence of least squares learning mechanisms in self-referential linear stochastic models, Abstract stochastic approximations and applications, On recursive estimation for hidden Markov models, Extremum seeking under stochastic noise and applications to mobile sensors, Convergence of algorithms used for principal component analysis, A smoothing stochastic algorithm for quantile estimation, Extremum seeking of dynamical systems via gradient descent and stochastic approximation methods, Stochastic approximation with two time scales, A space quantization method for numerical integration, Stochastic fictitious play with continuous action sets, Variance-constrained actor-critic algorithms for discounted and average reward MDPs, Convergence proof of matrix dynamics for online linear discriminant analysis, A second-order iterated smoothing algorithm, Iterated filtering, Weak convergence of Markov chain sampling methods and annealing algorithms to diffusions, Algorithmes stochastiques à bruit dépendant (Dependent noise for stochastic algorithms)., Convergence of a stochastic approximation algorithm for the GI/G/1 queue using infinitesimal perturbation analysis, Stabilization of stochastic approximation by step size adaptation, A case study of an adaptive load balancing algorithm, A simplified neuron model as a principal component analyzer, Generalization of a result of Fabian on the asymptotic normality of stochastic approximation, Contractivity of a Markov operator on the space of normalised positive distributions, Control: a perspective, Stochastic approximation with dependent noise, Reinforcement learning for long-run average cost., On learning multicategory classification with sample queries., Convergent multiple-timescales reinforcement learning algorithms in normal form games, Convergence in models with bounded expected relative hazard rates, Newton-based stochastic optimization using \(q\)-Gaussian smoothed functional algorithms, IPA for continuous stochastic marked graphs, Convergence theorems for the Kohonen feature mapping algorithms with VLRPs, Almost sure convergence of randomly truncated stochastic algorithms under verifiable condi\-tions, Stochastic approximation, cooperative dynamics and supermodular games, Multiclass classification and gene selection with a stochastic algorithm, Stochastic quasigradient methods for optimization of discrete event systems, Gradient estimates for the performance of Markov chains and discrete event processes, Generalized surrogate problem methodology for online stochastic discrete optimization, Adaptive algorithms for first principal eigenvector computation, Monte Carlo algorithms for optimal stopping and statistical learning, Efficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithm, Analysis of an identification algorithm arising in the adaptive estimation of Markov chains, A stopping rule for the Robbins-Monro method, The stochastic approximation method for the estimation of a multivariate probability density, Adaptation and tracking in system identification - a survey, Sharp convergence rates of stochastic approximation for degenerate roots, Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size, Topological orbital equivalence with asymptotic phase for a two time- scales discrete-time system, Nonparametric adaptive learning with feedback, Stochastic gradient algorithm with random truncations, Stochastic approximation algorithms with constant step size whose average is cooperative, Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing, Asymptotic behavior of self-organizing maps with nonuniform stimuli distribution, Natural actor-critic algorithms, Nondifferential optimization via adaptive smoothing, Theory and applications of adaptive control - a survey, Dynamical systems and variational inequalities, Stochastic programming in water management: A case study and a comparison of solution techniques, Convergence of stochastic approximation coupled with perturbation analysis in a class of manufacturing flow control models, Inexact subgradient methods with applications in stochastic programming, Recursive identification in continuous-time stochastic processes, Asymptotic normality of the continuous-time stochastic approximation algorithm, About Gaussian schemes in stochastic approximation, On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix, Simulated annealing type algorithms for multivariate optimization, On a continuous time stochastic approximation problem, Théorèmes de convergence presque sure pour une classe d'algorithmes stochastiques à pas decroissant, Neurodynamics and nonlinear integrable systems of Lax type, Online sparse sliced inverse regression for high-dimensional streaming data, Asynchronous stochastic approximation with differential inclusions, Recursive estimation algorithms for power controls of wireless communication networks, Regret bounds for Narendra-Shapiro bandit algorithms, A New Recursive Estimation Method for Single Input Single Output Models, Zeroth-order optimization with orthogonal random directions, Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning, Risk-Sensitive Reinforcement Learning via Policy Gradient Search, Simultaneous perturbation stochastic approximation: towards one-measurement per iteration, Convergence of stochastic approximation via martingale and converse Lyapunov methods, Stochastic approximation with discontinuous dynamics, differential inclusions, and applications, Invariance properties of the natural gradient in overparametrised systems, Convergence of the Kiefer–Wolfowitz algorithm in the presence of discontinuities, Multi-agent natural actor-critic reinforcement learning algorithms, Nonsmooth optimization by Lie bracket approximations into random directions, Stochastic approximation procedures for Lévy-driven SDEs, Convergence of gradient algorithms for nonconvex \(C^{1+ \alpha}\) cost functions, A randomized multi-index sequential Monte Carlo method, A Concentration Bound for Stochastic Approximation via Alekseev’s Formula, Improving reinforcement learning algorithms: Towards optimal learning rate policies, Independent learning in stochastic games, A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data, Pole assignment for stochastic systems with unknown coefficients, Online surrogate problem methodology for stochastic discrete resource allocation problem., Geometric structure in stochastic approximation, A simulation‐based algorithm for optimal pricing policy under demand uncertainty, Random-direction optimization algorithms with applications to threshold controls, Asymptotically efficient recursive estimation for incomplete data models using the observed information., The actor-critic algorithm as multi-time-scale stochastic approximation., Stochastic approximation algorithms: overview and recent trends., Convergence of least squares learning in self-referential discontinuous stochastic models., Minimization algorithms based on supervisor and searcher cooperation, Annealing adaptive search, cross-entropy, and stochastic approximation in global optimization, Finite-temperature coarse-graining of one-dimensional models: mathematical analysis and computational approaches, Simulation Optimization Using Multi-Time-Scale Adaptive Random Search, A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares), Unnamed Item, STOCK LIQUIDATION VIA STOCHASTIC APPROXIMATION USING NASDAQ DAILY AND INTRA‐DAY DATA, Multiscale Stochastic Approximation for Parametric Optimization of Hidden Markov Models, Actor-Critic Algorithms with Online Feature Adaptation, Smoothed Functional Algorithms for Stochastic Optimization Using q -Gaussian Distributions, Convergence rate of linear two-time-scale stochastic approximation., When can the two-armed bandit algorithm be trusted?, Sur quelques algorithmes récursifs pour les probabilités numériques, A partial history of the early development of continuous-time nonlinear stochastic systems theory, Broadcast control of multi-agent systems, Extremum seeking-based optimal EGR set-point design for combustion engines in lean-burn mode, On two numerical problems in applied probability : discretization of Stochastic Differential Equations and optimization of an expectation depending on a parameter, Choices and intervals, Two approaches to optimal routing and admission control in systems with real-time traffic, On convergence of adaptive estimation procedures with time delays, Quantile estimation with adaptive importance sampling, Actor-Critic–Like Stochastic Adaptive Search for Continuous Simulation Optimization, Optimal Learning for Nonlinear Parametric Belief Models Over Multidimensional Continuous Spaces, Learning competitive market balance, An adaptive optimization scheme with satisfactory transient performance, Rates of convergence of semi-stochastic approximation procedures for solving stochastic optimization problems, Scheduling policies using marked/phantom slot algorithms, Optimal posting price of limit orders: learning by trading, Approximate consensus in the dynamic stochastic network with incomplete information and measurement delays, Distributed Stochastic Approximation with Local Projections, The multivariate Révész's online estimator of a regression function and its averaging, Unnamed Item, Unnamed Item, ITERATIVE AND RECURSIVE ESTIMATION OF TRANSFER FUNCTIONS, Continuous-time constrained least-squares algorithms for recursive parameter estimation of stochastic linear systems by a stabilized output-error method, Numerical minimization methods for convex functionals dependent on probability measures with applications to optimal pollution monitoring, Asymptotic pseudotrajectories and chain recurrent flows, with applications, Network games; adaptations to Nash-Cournot equilibrium, Convergence of a Distributed Kiefer-Wolfowitz Algorithm, On h–valued stochastic approximation: finite dimenstional projections, Convergence of stochastic flows connected with stochastic ordinary differential equations, Discrete variable stochastic approximation procedures and recursive autoregressive model identification, On convergence of adaptive estimation procedures with time delays, Unnamed Item, Real time estimation of stochastic volatility processes, Optimization with Reference-Based Robust Preference Constraints, Approximate stochastic annealing for online control of infinite horizon Markov decision processes, Unnamed Item, A new hybrid stochastic approximation algorithm, Bridging the gap between constant step size stochastic gradient descent and Markov chains, Dynamics of Morse-Smale urn processes, Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement, Discrete non-linear adaptive data driven control based upon simultaneous perturbation stochastic approximation, Online estimation of integrated squared density derivatives, A unified framework for stochastic optimization, Markovian stochastic approximation with expanding projections, Continuous-time stochastic approximation: Convergence and asymptotic efficiency, Stochastic optimisation with inequality constraints using simultaneous perturbations and penalty functions, Decreasing the sensitivity of open-loop optimal solutions in decision making under uncertainty, A companion for the Kiefer-Wolfowitz-Blum stochastic approximation algorithm, Convergence of a stochastic subgradient method with averaging for nonsmooth nonconvex constrained optimization, Negatively reinforced balanced urn schemes, Optimal Learning with Local Nonlinear Parametric Models over Continuous Designs, On a multistage discrete stochastic optimization problem with stochastic constraints and nested sampling, A stochastic approximation algorithm to compute bid prices for joint capacity allocation and overbooking over an airline network, Appointment scheduling and real-time sequencing strategies for patient unpunctuality, A compact law of the iterated logarithm for online estimator of hazard rate under random censoring, Robust hebbian learning and noisy principal component analysis, Simultaneous perturbation Newton algorithms for simulation optimization, A simultaneous perturbation weak derivative estimator for stochastic neural networks, Sufficient and necessary condition for the convergence of stochastic approximation algorithms, Stochastic approximation on Riemannian manifolds, Unnamed Item, Nonlinear randomized urn models: a stochastic approximation viewpoint, Stochastic proximal gradient methods for nonconvex problems in Hilbert spaces, On Recursive Estimation in Incomplete Data Models, A two Timescale Stochastic Approximation Scheme for Simulation-Based Parametric Optimization, Extremum Seeking Control with Two-Sided Stochastic Perturbations, Convergence of Markovian Stochastic Approximation with Discontinuous Dynamics, On the stability and convergence of a self-tuning controller, Optimal quadratic quantization for numerics: the Gaussian case, Stochastic approximation: from statistical origin to big-data, multidisciplinary applications, Recursive estimators of integrated squared density derivatives, Sensitivity Analysis for Monte Carlo Simulation of Option Pricing, Feasible direction methods for stochastic programming problems, Sensitivity analysis and optimization of stochastic Petri nets, Optimization via simulation: A review, Optimisation of a single-component maintenance system: A smoothed perturbation analysis approach, Convergence of a stochastic approximation version of the EM algorithm, On the almost sure asymptotic behaviour of stochastic algorithm, Simultaneous Perturbation Stochastic Approximation with Norm-Limited Update Vector, Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling, Stochastic algorithm for Bayesian mixture effect template estimation, Optimal step sizes in semi-stochastic approximation procedures. II, \({\mathcal Q}\)-learning, Large deviations analysis of reflected diffusions and constrained stochastic approximation algorithms in convex sets^†, Strong representation of an adaptive stochastic approximation procedure, Stochastic approximation algorithm for minimax problems, A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization, An analysis of convergence for a learning version of the subspace method, On W.P.1 Convergence of A Parallel Stochastic Approximation Algorithm, Almost sure convergence of randomized urn models with application to elephant random walk, Stochastic approximation with random step sizes and urn models with random replacement matrices having finite mean, Unnamed Item, Introduction to learning and bounded rationality. (Preface to the special issue.), Learning aspiration in repeated games, A stochastic approximation from dependent observations, Gradient procedures for stochastic approximation with dependent noise and their asymptotic behaviour, Self-tuning controllers: non-square systems and convergence, Stochastic optimization on social networks with application to service pricing