Rates of Convergence for Stochastic Approximation Type Algorithms

DOI10.1137/0317043zbMath0418.93093OpenAlexW1989240959MaRDI QIDQ3852091

Harold J. Kushner, Hai Huang

Publication date: 1979

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/0317043

zbMATH Keywords

adaptive controlGaussian diffusionstochastic approximation algorithmidentification problems

Mathematics Subject Classification ID

Adaptive control/observation systems (93C40) Identification in stochastic control theory (93E12) Stochastic approximation (62L20)

Related Items

Conditional tail probabilities in continuous-time martingale LLN with application to parameter estimation in diffusions, Sur quelques algorithmes récursifs pour les probabilités numériques, A New Recursive Estimation Method for Single Input Single Output Models, Artificial neural networks: an econometric perspective^∗, Rates of convergence of adaptive step-size of stochastic approximation algorithms, Central limit theorems for stochastic approximation with controlled Markov chain dynamics, Adaptation and tracking in system identification - a survey, Derivative-free optimization methods, Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing, Near-optimal solutions of convex semi-infinite programs via targeted sampling