Simple conditions for convergence of sequential Monte Carlo genealogies with applications

06/30/2020
by   Suzie Brown, et al.
0

Sequential Monte Carlo algorithms are popular methods for approximating integrals in problems such as non-linear filtering and smoothing. Their performance depends strongly on the properties of an induced genealogical process. We present simple conditions under which the limiting process, as the number of particles grows, is a time-rescaled Kingman coalescent. We establish these conditions for standard sequential Monte Carlo with a broad class of low-variance resampling schemes, as well as for conditional sequential Monte Carlo with multinomial resampling.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/23/2018

Adaptive Tuning Of Hamiltonian Monte Carlo Within Sequential Monte Carlo

Sequential Monte Carlo (SMC) samplers form an attractive alternative to ...
research
08/25/2022

Convergence of random-weight sequential Monte Carlo methods

We investigate the properties of a sequential Monte Carlo method where t...
research
01/18/2018

Monte Carlo Computation for Generalized Linear Model

Monte Carlo method is a broad class of computational algorithms that rel...
research
10/29/2021

The divide-and-conquer sequential Monte Carlo algorithm: theoretical properties and limit theorems

We revisit the divide-and-conquer sequential Monte Carlo (DaC-SMC) algor...
research
07/14/2021

Numerical investigation of reversed gas feed configurations for Hall thrusters

A reversed gas feed configuration for Hall thrusters is proposed and stu...
research
05/30/2022

Critic Sequential Monte Carlo

We introduce CriticSMC, a new algorithm for planning as inference built ...
research
01/03/2018

Optimal Learning from the Doob-Dynkin lemma

The Doob-Dynkin Lemma gives conditions on two functions X and Y that ens...

Please sign up or login with your details

Forgot password? Click here to reset