2025/12/22 by Jonas Arruda, Arruda, Jonas, Niels Bracher +7 · 2 voices · 3 citations
Computer Science · Mathematics · Physics and Astronomy · #Consistency (knowledge bases) #Diffusion #Estimation theory #Generative Adversarial Networks and Image Synthesis #Inference #Joint (building) #Markov Chains and Monte Carlo Methods #Model Reduction and Neural Networks #Noise (video) #Statistical inference #cs.LG #stat.ME #stat.ML
paper · pdf · doi:10.48550/arxiv.2512.20685
published in Open MIND
openalex publication_date 2025/12/22 · openalex created_date 2025/12/26 · openalex updated_date 2026/07/28
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.