Diffusion Models in Simulation-Based Inference: A Tutorial Review
It provides a comprehensive guide for researchers and practitioners applying diffusion models to simulation-based inference, but is a review rather than novel research.
This tutorial review synthesizes recent developments on diffusion models for simulation-based inference, covering design choices and highlighting opportunities from concepts like guidance and flow matching, while discussing efficiency and accuracy trade-offs.
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.