Stochastic approximation with random step sizes and urn models with random replacement matrices having finite mean
DOI10.1214/18-AAP1441zbMath1435.62311arXiv1709.00467OpenAlexW2963199393WikidataQ127445121 ScholiaQ127445121MaRDI QIDQ2330454
Ujan Gangopadhyay, Krishanu Maulik
Publication date: 22 October 2019
Published in: The Annals of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1709.00467
stochastic approximationuniform integrabilityirreducibilityurn modelrandom driftLotka-Volterra differential equationrandom replacement matrixbalanced replacement matrixrandom step size
Martingales with discrete parameter (60G42) Strong limit theorems (60F15) Stochastic approximation (62L20)
Related Items (4)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Randomized urn models revisited using stochastic approximation
- Strong laws for urn models with balanced replacement matrices
- Central limit theorems of a recursive stochastic algorithm with applications to adaptive designs
- Stochastic approximation. A dynamical systems viewpoint.
- Stochastic approximation methods for constrained and unconstrained systems
- Asymptotics in randomized urn models
- The Gaussian approximation for generalized Friedman's urn model with heterogeneous and unbalanced updating
- Non-negative matrices and Markov chains.
- Multidimensional diffusion processes.
- Strong convergence of proportions in a multicolor Pólya urn
- Continuity of the Perron root
- Bernard Friedman's Urn
- Embedding of Urn Schemes into Continuous Time Markov Branching Processes and Related Limit Theorems
- A Stochastic Approximation Method
This page was built for publication: Stochastic approximation with random step sizes and urn models with random replacement matrices having finite mean