Central limit theorems of a recursive stochastic algorithm with applications to adaptive designs

DOI10.1214/16-AAP1187zbMATH Open1358.60044arXiv1602.05708OpenAlexW3104630436MaRDI QIDQ511483FDOQ511483

Lixin Zhang

Publication date: 21 February 2017

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Abstract: Stochastic approximation algorithms have been the subject of an enormous body of literature, both theoretical and applied. Recently, Laruelle and Pag`es (2013) presented a link between the stochastic approximation and response-adaptive designs in clinical trials based on randomized urn models investigated in Bai and Hu (1999, 2005), and derived the asymptotic normality or central limit theorem for the normalized procedure using a central limit theorem for the stochastic approximation algorithm. However, the classical central limit theorem for the stochastic approximation algorithm does not include all cases of its regression function, creating a gap between the results of Laruelle and Pag`es (2013) and those of Bai and Hu (2005) for randomized urn models. In this paper, we establish new central limit theorems of the stochastic approximation algorithm under the popular Lindeberg condition to fill this gap. Moreover, we prove that the process of the algorithms can be approximated by a Gaussian process that is a solution of a stochastic differential equation. In our application, we investigate a more involved family of urn models and related adaptive designs in which it is possible to remove the balls from the urn, and the expectation of the total number of balls updated at each stage is not necessary a constant. The asymptotic properties are derived under much less stringent assumptions than those in Bai and Hu (1999, 2005) and Laruelle and Pag`es (2013).

Full work available at URL: https://arxiv.org/abs/1602.05708

Recommendations

• Randomized urn models revisited using stochastic approximation
• Adaptive designs and Robbins-Monro algorithm
• Nonlinear randomized urn models: a stochastic approximation viewpoint
• Non-standard limit theorems for urn models and stochastic approximation procedures
• Central limit theorem for an adaptive randomly reinforced urn model

zbMATH Keywords

Gaussian approximationcentral limit theoremstochastic differential equationurn modeladaptive designstochastic approximation algorithms

Mathematics Subject Classification ID

Gaussian processes (60G15) Central limit and other weak theorems (60F05) Stochastic approximation (62L20) Strong limit theorems (60F15) Functional limit theorems; invariance principles (60F17) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10)

Cited In (12)

• Nonlinear randomized urn models: a stochastic approximation viewpoint
• Nonparametric covariate-adjusted response-adaptive design based on a functional urn model
• Generalized rescaled Pólya urn and its statistical application
• Diffusion of binary opinions in a growing population with heterogeneous behaviour and external influence
• Negatively reinforced balanced urn schemes
• Stochastic approximation on noncompact measure spaces and application to measure-valued Pólya processes
• Interacting nonlinear reinforced stochastic processes: Synchronization or non-synchronization
• Interacting urns on a finite directed graph
• Approximating the operating characteristics of Bayesian uncertainty directed trial designs
• Multiple drawing multi-colour urns by stochastic approximation
• Urns with multiple drawings and graph-based interaction
• Stochastic approximation with random step sizes and urn models with random replacement matrices having finite mean

This page was built for publication: Central limit theorems of a recursive stochastic algorithm with applications to adaptive designs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q511483)