Sampling Conditionally on a Rare Event via Generalized Splitting

09/08/2019
by   Zdravko I. Botev, et al.
0

We propose and analyze a generalized splitting method to sample approximately from a distribution conditional on the occurrence of a rare event. This has important applications in a variety of contexts in operations research, engineering, and computational statistics. The method uses independent trials starting from a single particle. We exploit this independence to obtain asymptotic and non-asymptotic bounds on the total variation error of the sampler. Our main finding is that the approximation error depends crucially on the relative variability of the number of points produced by the splitting algorithm in one run, and that this relative variability can be readily estimated via simulation. We illustrate the relevance of the proposed method on an application in which one needs to sample (approximately) from an intractable posterior density in Bayesian inference.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/09/2023

Stein Variational Rare Event Simulation

Rare event simulation and rare event probability estimation are importan...
research
10/19/2017

Importance sampling the union of rare events with an application to power systems analysis

This paper presents a method for estimating the probability μ of a union...
research
06/15/2023

Estimating the Sampling Distribution of Test-Statistics in Bayesian Clinical Trials

Bayesian inference and the use of posterior or posterior predictive prob...
research
08/11/2019

Finite Sample Hypothesis Tests for Stacked Estimating Equations

Suppose there are two unknown parameters, each parameter is the solution...
research
10/25/2021

Over-Conservativeness of Variance-Based Efficiency Criteria and Probabilistic Efficiency in Rare-Event Simulation

In rare-event simulation, an importance sampling (IS) estimator is regar...
research
09/19/2022

Normal approximation for the posterior in exponential families

In this paper we obtain quantitative Bernstein-von Mises type bounds on ...
research
08/08/2022

An integer grid bridge sampler for the Bayesian inference of incomplete birth-death records

A one-to-one correspondence is established between the bridge path space...

Please sign up or login with your details

Forgot password? Click here to reset