Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flows

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Crucinio, Francesca R., Pathiraja, Sahani
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918329428475904
author Crucinio, Francesca R.
Pathiraja, Sahani
author_facet Crucinio, Francesca R.
Pathiraja, Sahani
contents We consider the problem of sampling from a probability distribution $π$. It is well known that this can be written as an optimisation problem over the space of probability distribution in which we aim to minimise the Kullback--Leibler divergence from $π$. We consider several partial differential equations (PDEs) whose solution is a minimiser of the Kullback--Leibler divergence from $π$ and connect them to well-known Monte Carlo algorithms. We focus in particular on PDEs obtained by considering the Wasserstein--Fisher--Rao geometry over the space of probabilities and show that these lead to a natural implementation using importance sampling and sequential Monte Carlo. We propose a novel algorithm to approximate the Wasserstein--Fisher--Rao flow of the Kullback--Leibler divergence and conduct an extensive empirical study to identify when these algorithms outperforms other popular Monte Carlo algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05905
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flows
Crucinio, Francesca R.
Pathiraja, Sahani
Methodology
Numerical Analysis
Computation
Machine Learning
65C05, 62F15
We consider the problem of sampling from a probability distribution $π$. It is well known that this can be written as an optimisation problem over the space of probability distribution in which we aim to minimise the Kullback--Leibler divergence from $π$. We consider several partial differential equations (PDEs) whose solution is a minimiser of the Kullback--Leibler divergence from $π$ and connect them to well-known Monte Carlo algorithms. We focus in particular on PDEs obtained by considering the Wasserstein--Fisher--Rao geometry over the space of probabilities and show that these lead to a natural implementation using importance sampling and sequential Monte Carlo. We propose a novel algorithm to approximate the Wasserstein--Fisher--Rao flow of the Kullback--Leibler divergence and conduct an extensive empirical study to identify when these algorithms outperforms other popular Monte Carlo algorithms.
title Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flows
topic Methodology
Numerical Analysis
Computation
Machine Learning
65C05, 62F15
url https://arxiv.org/abs/2506.05905