mlsanityData to 14 Oct 2026

ConDiSim: Conditional Diffusion Models for Simulation Based Inference

arXiv 2505.08403 ↗First posted 13 May 2025cs.LG cs.AI stat.MLcited by 2

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 32 of its 48 references that are in the map. First posted on arXiv 13 May 2025.

Builds on

32 of 48 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Efficient Diffusion Training via Min-SNR Weighting Strategy16 Mar
  2. 2022Classifier-Free Diffusion Guidance26 Jul
  3. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  5. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 27

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  5. 2015Variational Inference with Normalizing Flowscited by 2,170
  6. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  7. 2019The frontier of simulation-based inferencecited by 502
  8. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  9. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 384
  10. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 221
  11. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 219
  12. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 163
15 more
  1. 2021Benchmarking Simulation-Based Inferencecited by 162
  2. 2018Validating Bayesian Inference Algorithms with Simulation-Based Calibrationcited by 124
  3. 2023Flow Matching for Scalable Simulation-Based Inferencecited by 101
  4. 2024All-in-one simulation-based inferencecited by 74
  5. 2021Simulation Intelligence: Towards a New Generation of Scientific Methodscited by 68
  6. 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
  7. 2015Learning Summary Statistic for Approximate Bayesian Computation via Deep Neural Networkcited by 39
  8. 2024Neural Methods for Amortized Inferencecited by 39
  9. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  10. 2023BayesFlow: Amortized Bayesian Workflows With Neural Networkscited by 32
  11. 2021Graphical Test for Discrete Uniformity and its Applications in Goodness of Fit Evaluation and Multiple Sample Comparisoncited by 26
  12. 2024Diffusion posterior sampling for simulation-based inference in tall data settingscited by 19
  13. 2022Neural Posterior Estimation with Differentiable Simulatorscited by 9
  14. 2020Convolutional Neural Networks as Summary Statistics for Approximate Bayesian Computationcited by 8
  15. 2021Robust and integrative Bayesian neural networks for likelihood-free parameter inferencecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarioscited by 1
  2. 2026Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion Models in Simulation-Based Inference: A Tutorial Review
  2. 2024Conditioning diffusion models by explicit forward-backward bridging
  3. 2026Stochastic Transition-Map Distillation for Fast Probabilistic Inference
  4. 2024DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transform
  5. 2025EVODiff: Entropy-aware Variance Optimized Diffusion Inference
  6. 2025Diffusion Models: A Mathematical Introduction
  7. 2026Tempered Guided Diffusion
  8. 2024Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors