Asymptotic behavior of constrained stochastic approximations via the theory of large deviations

DOI10.1007/BF00354035zbMath0599.60028MaRDI QIDQ1080265

Paul Dupuis, Harold J. Kushner

Publication date: 1987

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

zbMATH Keywords

asymptotic normality; escape times; asymptotic convergence properties; large deviations methods

Mathematics Subject Classification ID

62L20: Stochastic approximation

60F10: Large deviations

Related Items

Large deviations analysis of reflected diffusions and constrained stochastic approximation algorithms in convex sets^†, Stochastic optimisation with inequality constraints using simultaneous perturbations and penalty functions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic approximation methods for constrained and unconstrained systems
• Selection theorems and their applications
• THE AVERAGING PRINCIPLE AND THEOREMS ON LARGE DEVIATIONS
• On Upper Functions for Stochastic Approximation Procedures
• An Invariant Measure Approach to the Convergence of Stochastic Approximations with State Dependent Noise
• Robustness and Approximation of Escape Times and Large Deviations Estimates for Systems with Small Noise Effects
• Stochastic Approximations via Large Deviations: Asymptotic Properties
• Stochastic Approximation in Hilbert Space: Identification and Optimization of Linear Continuous Parameter Systems
• Stochastic Minimization with Constant Step-Size: Asymptotic Laws