Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sharrock, Louis, Simons, Jack, Liu, Song, Beaumont, Mark
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917682112102400
author Sharrock, Louis
Simons, Jack
Liu, Song
Beaumont, Mark
author_facet Sharrock, Louis
Simons, Jack
Liu, Song
Beaumont, Mark
contents We introduce Sequential Neural Posterior Score Estimation (SNPSE), a score-based method for Bayesian inference in simulator-based models. Our method, inspired by the remarkable success of score-based methods in generative modelling, leverages conditional score-based diffusion models to generate samples from the posterior distribution of interest. The model is trained using an objective function which directly estimates the score of the posterior. We embed the model into a sequential training procedure, which guides simulations using the current approximation of the posterior at the observation of interest, thereby reducing the simulation cost. We also introduce several alternative sequential approaches, and discuss their relative merits. We then validate our method, as well as its amortised, non-sequential, variant on several numerical examples, demonstrating comparable or superior performance to existing state-of-the-art methods such as Sequential Neural Posterior Estimation (SNPE).
format Preprint
id arxiv_https___arxiv_org_abs_2210_04872
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models
Sharrock, Louis
Simons, Jack
Liu, Song
Beaumont, Mark
Machine Learning
We introduce Sequential Neural Posterior Score Estimation (SNPSE), a score-based method for Bayesian inference in simulator-based models. Our method, inspired by the remarkable success of score-based methods in generative modelling, leverages conditional score-based diffusion models to generate samples from the posterior distribution of interest. The model is trained using an objective function which directly estimates the score of the posterior. We embed the model into a sequential training procedure, which guides simulations using the current approximation of the posterior at the observation of interest, thereby reducing the simulation cost. We also introduce several alternative sequential approaches, and discuss their relative merits. We then validate our method, as well as its amortised, non-sequential, variant on several numerical examples, demonstrating comparable or superior performance to existing state-of-the-art methods such as Sequential Neural Posterior Estimation (SNPE).
title Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models
topic Machine Learning
url https://arxiv.org/abs/2210.04872