Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Konakov, Valentin, Mammen, Enno, Huang, Lorick
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2304.10673
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914104533319680
author Konakov, Valentin
Mammen, Enno
Huang, Lorick
author_facet Konakov, Valentin
Mammen, Enno
Huang, Lorick
contents The Robbins-Monro algorithm is a recursive, simulation-based stochastic procedure to approximate the zeros of a function that can be written as an expectation. It is known that under some technical assumptions, Gaussian limit distributions approximate the stochastic performance of the algorithm. Here, we are interested in strong approximations for Robbins-Monro procedures. The main tool for getting them are local limit theorems, that is, studying the convergence of the density of the algorithm. The analysis relies on a version of parametrix techniques for Markov chains converging to diffusions. The main difficulty that arises here is the fact that the drift is unbounded.
format Preprint
id arxiv_https___arxiv_org_abs_2304_10673
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Local Limit Theorems and Strong Approximations for Robbins-Monro Procedures
Konakov, Valentin
Mammen, Enno
Huang, Lorick
Probability
The Robbins-Monro algorithm is a recursive, simulation-based stochastic procedure to approximate the zeros of a function that can be written as an expectation. It is known that under some technical assumptions, Gaussian limit distributions approximate the stochastic performance of the algorithm. Here, we are interested in strong approximations for Robbins-Monro procedures. The main tool for getting them are local limit theorems, that is, studying the convergence of the density of the algorithm. The analysis relies on a version of parametrix techniques for Markov chains converging to diffusions. The main difficulty that arises here is the fact that the drift is unbounded.
title Local Limit Theorems and Strong Approximations for Robbins-Monro Procedures
topic Probability
url https://arxiv.org/abs/2304.10673