ConDiSim: Conditional Diffusion Models for Simulation Based Inference

2025/05/13 by Nautiyal, Mayank, Hellander, Andreas, Singh, Prashant
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2505.08403

Abstract

We present a conditional diffusion model - ConDiSim, for simulation-based inference of complex systems with intractable likelihoods. ConDiSim leverages denoising diffusion probabilistic models to approximate posterior distributions, consisting of a forward process that adds Gaussian noise to parameters, and a reverse process learning to denoise, conditioned on observed data. This approach effectively captures complex dependencies and multi-modalities within posteriors. ConDiSim is evaluated across ten benchmark problems and two real-world test problems, where it demonstrates effective posterior approximation accuracy while maintaining computational efficiency and stability in model training. ConDiSim offers a robust and extensible framework for simulation-based inference, particularly suitable for parameter inference workflows requiring fast inference methods.

Related

• Diffusion Models in Simulation-Based Inference: A Tutorial Review
• Conditioning diffusion models by explicit forward-backward bridging
• Diffusion models as plug-and-play priors
• Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
• Diffusion Models: A Mathematical Introduction