Stochastic Approximation and Large Deviations: Upper Bounds and <scp>w.p.1</scp> Convergence

DOI10.1137/0327059zbMath0679.60041OpenAlexW2156948165MaRDI QIDQ4729096

Harold J. Kushner, Paul Dupuis

Publication date: 1989

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

Full work available at URL: https://doi.org/10.1137/0327059

zbMATH Keywords

large deviationserrors for tracking systemsstochastic recursive approximation algorithms

Mathematics Subject Classification ID

Estimation and detection in stochastic control theory (93E10) Identification in stochastic control theory (93E12) Stochastic approximation (62L20) Large deviations (60F10)

Related Items (16)

Conditional tail probabilities in continuous-time martingale LLN with application to parameter estimation in diffusions ⋮ Convergence properties of ordinal comparison in the simulation of discrete event dynamic systems ⋮ Learning and equilibrium transitions: stochastic stability in discounted stochastic fictitious play ⋮ High‐dimensional limit theorems for SGD: Effective dynamics and critical scaling ⋮ Escapist policy rules ⋮ Escape dynamics: a continuous-time approximation ⋮ Exact bounds for the rate of convergence in general stochastic approximation procedures ⋮ On the convergence of reinforcement learning ⋮ Stochastic approximation algorithms: overview and recent trends. ⋮ Convergence of least squares learning in self-referential discontinuous stochastic models. ⋮ Importance sampling for a Markov modulated queuing network ⋮ An almost sure central limit theorem for stochastic approximation algorithms ⋮ A stopping rule for the Robbins-Monro method ⋮ Rate of convergence of stochastic approximation procedures in a Banach space ⋮ Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing ⋮ Dynamical systems and variational inequalities

This page was built for publication: Stochastic Approximation and Large Deviations: Upper Bounds and <scp>w.p.1</scp> Convergence