Stochastic approximation methods for constrained and unconstrained systems

From MaRDI portal
Revision as of 08:41, 31 January 2024 by Import240129110113 (talk | contribs) (Created automatically from import240129110113)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Publication:1248264

zbMath0381.60004MaRDI QIDQ1248264

Dean S. Clark, Harold J. Kushner

Publication date: 1978

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




Related Items (only showing first 100 items - show all)

A method combining genetic algorithm with simultaneous perturbation stochastic approximation for linearly constrained stochastic optimization problemsAsymptotic behavior of constrained stochastic approximations via the theory of large deviationsInventory models under uncertainty: An adaptive approachStochastic and robust control of nonlinear economic systemsOn convergence of the stochastic subgradient method with on-line stepsize rulesOptimal load sharing in soft real-time systems using likelihood ratiosAn algorithm with randomly varying truncation for adaptive beam-formersA constrained optimization perspective on actor-critic algorithms and application to network routingStochastic forward-backward splitting for monotone inclusionsOn stochastic extremum seeking via adaptive perturbation-demodulation loopApproximation of the initial reserve for known ruin probabilitiesAn online prediction algorithm for reinforcement learning with linear function approximation using cross entropy methodConvergence and robustness of the Robbins-Monro algorithm truncated at randomly varying boundsMultiscale Q-learning with linear function approximationA combined direction stochastic approximation algorithmA combined algorithm for identification and approximationOnline estimation of hazard rate under random censoringStrong consistency of recursive identification by no use of persistent excitation conditionMinimizing noisy functionals in Hilbert space: An extension of the Kiefer-Wolfowitz procedureOptimization of discrete variable stochastic systems by computer simulationAdaptive filters with constraints and correlated non-stationary signalsConvergence properties of ordinal comparison in the simulation of discrete event dynamic systemsConstrained optimization via stochastic approximation with a simultaneous perturbation gradient approximationLearning in linear models with expectational leadsOn the choice of step size in the Robbins-Monro procedureConvergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithmsWeighted averaging and stochastic approximationRates of convergence of ordinal comparison for dependent discrete event dynamic systemsLinear programming with stochastic elements: An on-line approachAlmost sure convergence of Titterington's recursive estimator for mixture modelsOn a proof of Robbins-Monro algorithmRandomized urn models revisited using stochastic approximationA simulation optimization method that considers uncertainty and multiple performance measuresConvergence of least squares learning mechanisms in self-referential linear stochastic modelsAbstract stochastic approximations and applicationsOn recursive estimation for hidden Markov modelsExtremum seeking under stochastic noise and applications to mobile sensorsConvergence of algorithms used for principal component analysisA smoothing stochastic algorithm for quantile estimationExtremum seeking of dynamical systems via gradient descent and stochastic approximation methodsStochastic approximation with two time scalesA space quantization method for numerical integrationStochastic fictitious play with continuous action setsVariance-constrained actor-critic algorithms for discounted and average reward MDPsConvergence proof of matrix dynamics for online linear discriminant analysisA second-order iterated smoothing algorithmIterated filteringWeak convergence of Markov chain sampling methods and annealing algorithms to diffusionsAlgorithmes stochastiques à bruit dépendant (Dependent noise for stochastic algorithms).Convergence of a stochastic approximation algorithm for the GI/G/1 queue using infinitesimal perturbation analysisStabilization of stochastic approximation by step size adaptationA case study of an adaptive load balancing algorithmA simplified neuron model as a principal component analyzerGeneralization of a result of Fabian on the asymptotic normality of stochastic approximationContractivity of a Markov operator on the space of normalised positive distributionsControl: a perspectiveStochastic approximation with dependent noiseReinforcement learning for long-run average cost.On learning multicategory classification with sample queries.Convergent multiple-timescales reinforcement learning algorithms in normal form gamesConvergence in models with bounded expected relative hazard ratesNewton-based stochastic optimization using \(q\)-Gaussian smoothed functional algorithmsIPA for continuous stochastic marked graphsConvergence theorems for the Kohonen feature mapping algorithms with VLRPsAlmost sure convergence of randomly truncated stochastic algorithms under verifiable condi\-tionsStochastic approximation, cooperative dynamics and supermodular gamesMulticlass classification and gene selection with a stochastic algorithmStochastic quasigradient methods for optimization of discrete event systemsGradient estimates for the performance of Markov chains and discrete event processesGeneralized surrogate problem methodology for online stochastic discrete optimizationAdaptive algorithms for first principal eigenvector computationMonte Carlo algorithms for optimal stopping and statistical learningEfficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithmAnalysis of an identification algorithm arising in the adaptive estimation of Markov chainsA stopping rule for the Robbins-Monro methodThe stochastic approximation method for the estimation of a multivariate probability densityAdaptation and tracking in system identification - a surveySharp convergence rates of stochastic approximation for degenerate rootsNon-asymptotic confidence bounds for stochastic approximation algorithms with constant step sizeTopological orbital equivalence with asymptotic phase for a two time- scales discrete-time systemNonparametric adaptive learning with feedbackStochastic gradient algorithm with random truncationsStochastic approximation algorithms with constant step size whose average is cooperativeWeak convergence rates for stochastic approximation with application to multiple targets and simulated annealingAsymptotic behavior of self-organizing maps with nonuniform stimuli distributionNatural actor-critic algorithmsNondifferential optimization via adaptive smoothingTheory and applications of adaptive control - a surveyDynamical systems and variational inequalitiesStochastic programming in water management: A case study and a comparison of solution techniquesConvergence of stochastic approximation coupled with perturbation analysis in a class of manufacturing flow control modelsInexact subgradient methods with applications in stochastic programmingRecursive identification in continuous-time stochastic processesAsymptotic normality of the continuous-time stochastic approximation algorithmAbout Gaussian schemes in stochastic approximationOn stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrixSimulated annealing type algorithms for multivariate optimizationOn a continuous time stochastic approximation problemThéorèmes de convergence presque sure pour une classe d'algorithmes stochastiques à pas decroissantNeurodynamics and nonlinear integrable systems of Lax type







This page was built for publication: Stochastic approximation methods for constrained and unconstrained systems