Diffusion Models in Simulation-Based Inference: A Tutorial Review

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Arruda, Jonas, Bracher, Niels, Köthe, Ullrich, Hasenauer, Jan, Radev, Stefan T.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910004779417600
author Arruda, Jonas
Bracher, Niels
Köthe, Ullrich
Hasenauer, Jan
Radev, Stefan T.
author_facet Arruda, Jonas
Bracher, Niels
Köthe, Ullrich
Hasenauer, Jan
Radev, Stefan T.
contents Diffusion models have recently emerged as powerful learners for simulation-based inference (SBI), enabling fast and accurate estimation of latent parameters from simulated and real data. Their score-based formulation offers a flexible way to learn conditional or joint distributions over parameters and observations, thereby providing a versatile solution to various modeling problems. In this tutorial review, we synthesize recent developments on diffusion models for SBI, covering design choices for training, inference, and evaluation. We highlight opportunities created by various concepts such as guidance, score composition, flow matching, consistency models, and joint modeling. Furthermore, we discuss how efficiency and statistical accuracy are affected by noise schedules, parameterizations, and samplers. Finally, we illustrate these concepts with case studies across parameter dimensionalities, simulation budgets, and model types, and outline open questions for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20685
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diffusion Models in Simulation-Based Inference: A Tutorial Review
Arruda, Jonas
Bracher, Niels
Köthe, Ullrich
Hasenauer, Jan
Radev, Stefan T.
Machine Learning
Methodology
Diffusion models have recently emerged as powerful learners for simulation-based inference (SBI), enabling fast and accurate estimation of latent parameters from simulated and real data. Their score-based formulation offers a flexible way to learn conditional or joint distributions over parameters and observations, thereby providing a versatile solution to various modeling problems. In this tutorial review, we synthesize recent developments on diffusion models for SBI, covering design choices for training, inference, and evaluation. We highlight opportunities created by various concepts such as guidance, score composition, flow matching, consistency models, and joint modeling. Furthermore, we discuss how efficiency and statistical accuracy are affected by noise schedules, parameterizations, and samplers. Finally, we illustrate these concepts with case studies across parameter dimensionalities, simulation budgets, and model types, and outline open questions for future research.
title Diffusion Models in Simulation-Based Inference: A Tutorial Review
topic Machine Learning
Methodology
url https://arxiv.org/abs/2512.20685