Briding Diffusion Posterior Sampling and Monte Carlo methods: a survey

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Janati, Yazid, Durmus, Alain, Olsson, Jimmy, Moulines, Eric
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909849644695552
author Janati, Yazid
Durmus, Alain
Olsson, Jimmy
Moulines, Eric
author_facet Janati, Yazid
Durmus, Alain
Olsson, Jimmy
Moulines, Eric
contents Diffusion models enable the synthesis of highly accurate samples from complex distributions and have become foundational in generative modeling. Recently, they have demonstrated significant potential for solving Bayesian inverse problems by serving as priors. This review offers a comprehensive overview of current methods that leverage \emph{pre-trained} diffusion models alongside Monte Carlo methods to address Bayesian inverse problems without requiring additional training. We show that these methods primarily employ a \emph{twisting} mechanism for the intermediate distributions within the diffusion process, guiding the simulations toward the posterior distribution. We describe how various Monte Carlo methods are then used to aid in sampling from these twisted distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14114
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Briding Diffusion Posterior Sampling and Monte Carlo methods: a survey
Janati, Yazid
Durmus, Alain
Olsson, Jimmy
Moulines, Eric
Machine Learning
Diffusion models enable the synthesis of highly accurate samples from complex distributions and have become foundational in generative modeling. Recently, they have demonstrated significant potential for solving Bayesian inverse problems by serving as priors. This review offers a comprehensive overview of current methods that leverage \emph{pre-trained} diffusion models alongside Monte Carlo methods to address Bayesian inverse problems without requiring additional training. We show that these methods primarily employ a \emph{twisting} mechanism for the intermediate distributions within the diffusion process, guiding the simulations toward the posterior distribution. We describe how various Monte Carlo methods are then used to aid in sampling from these twisted distributions.
title Briding Diffusion Posterior Sampling and Monte Carlo methods: a survey
topic Machine Learning
url https://arxiv.org/abs/2510.14114