mlsanityData to 7 Oct 2026

Particle Denoising Diffusion Sampler

arXiv 2402.06320 ↗First posted 9 Feb 2024stat.ML cs.LG stat.COcited by 63

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate samples from the data distribution are then obtained by estimating the time-reversal of this diffusion using score matching ideas. We follow here a similar strategy to sample from unnormalized probability densities and compute their normalizing constants. However, the time-reversed diffusion is here simulated by using an original iterative particle scheme relying on a novel score matching loss. Contrary to standard denoising diffusion models, the resulting Particle Denoising Diffusion Sampler (PDDS) provides asymptotically consistent estimates under mild assumptions. We demonstrate PDDS on multimodal and high dimensional sampling tasks.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 24 of its 57 references that are in the map. First posted on arXiv 9 Feb 2024.

Builds on

24 of 57 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models19 Oct
  2. 2023Denoising Diffusion Samplers27 Feb
  3. 2022An optimal control perspective on diffusion-based generative modeling2 Nov
  4. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling1 Jun
  5. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 17

  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  2. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  3. 2023Practical and Asymptotically Exact Conditional Sampling in Diffusion Modelscited by 218
  4. 2021Path Integral Sampler: a stochastic control approach for samplingcited by 175
  5. 2022Flow Annealed Importance Sampling Bootstrapcited by 124
  6. 2023Improved sampling via learned diffusionscited by 103
  7. 2021Annealed Flow Transport Monte Carlocited by 90
  8. 2019NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transportcited by 73
  9. 2022Continual Repeated Annealed Flow Transport Monte Carlocited by 66
  10. 2023Monte Carlo guided Diffusion for Bayesian linear inverse problemscited by 65
  11. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
  12. 2023Reverse Diffusion Monte Carlocited by 41
5 more
  1. 2020An invitation to sequential Monte Carlo samplerscited by 33
  2. 2021Stein's Method Meets Computational Statistics: A Review of Some Recent Developmentscited by 32
  3. 2022SIXO: Smoothing Inference with Twisted Objectivescited by 22
  4. 2022On resampling schemes for particle filters with weakly informative observationscited by 5
  5. 2022Proposal of a Score Based Approach to Sampling Using Monte Carlo Estimation of Score and Oracle Access to Target Densitycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 35; 2026: 15.

63 papers.

Sort:

By area:

  1. 2024Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decodingcited by 127
  2. 2025Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Expertscited by 85
  3. 2025Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Reviewcited by 82
  4. 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matchingcited by 78
  5. 2024Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Designcited by 72
  6. 2024Sequential Controlled Langevin Diffusionscited by 47
  7. 2024DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transformcited by 44
  8. 2025Dynamic Search for Inference-Time Alignment in Diffusion Modelscited by 36
  9. 2026Q-learning with Adjoint Matchingcited by 33
  10. 2025Underdamped Diffusion Bridges with Applications to Samplingcited by 28
  11. 2025No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplerscited by 25
  12. 2025Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Modelscited by 23
38 more
  1. 2024Training Neural Samplers with Reverse Diffusive KL Divergencecited by 21
  2. 2025Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Designcited by 21
  3. 2025Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posteriorcited by 20
  4. 2025Adjoint Schr"odinger Bridge Samplercited by 20
  5. 2024Conditional sampling within generative diffusion modelscited by 18
  6. 2025Composition and Control with Distilled Energy Diffusion Models and Sequential Monte Carlocited by 18
  7. 2025From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster trainingcited by 17
  8. 2025RNE: plug-and-play diffusion inference-time control and energy-based trainingcited by 16
  9. 2025Proximal Diffusion Neural Samplercited by 16
  10. 2025FEAT: Free energy Estimators with Adaptive Transportcited by 15
  11. 2025CoDe: Blockwise Control for Denoising Diffusion Modelscited by 14
  12. 2025Accelerated Parallel Tempering via Neural Transportscited by 13
  13. 2025Progressive Tempering Sampler with Diffusioncited by 13
  14. 2024Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flowscited by 9
  15. 2024Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Seriescited by 9
  16. 2024Learned Reference-based Diffusion Sampling for multi-modal distributionscited by 9
  17. 2025Discrete Diffusion Trajectory Alignment via Stepwise Decompositioncited by 9
  18. 2025Non-equilibrium Annealed Adjoint Samplercited by 8
  19. 2025Learning Boltzmann Generators via Constrained Mass Transportcited by 8
  20. 2024Importance Corrected Neural JKO Samplingcited by 7
  21. 2025MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Modelscited by 7
  22. 2025Projected Coupled Diffusion for Test-Time Constrained Joint Generationcited by 6
  23. 2026Training-Free Adaptation of Diffusion Models via Doob's h-Transformcited by 6
  24. 2025Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidancecited by 5
  25. 2025Boltzmann generators for amorphous particle systemscited by 5
  26. 2024Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusioncited by 4
  27. 2025End-To-End Learning of Gaussian Mixture Priors for Diffusion Samplercited by 4
  28. 2025Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spacescited by 4
  29. 2025Control Variate Score Matching for Diffusion Modelscited by 4
  30. 2026Discrete Adjoint Schr"odinger Bridge Samplercited by 4
  31. 2026Flow Sampling: Learning to Sample from Unnormalized Densities via Denoising Conditional Processescited by 4
  32. 2024On diffusion posterior sampling via sequential Monte Carlo for zero-shot scaffolding of protein motifscited by 3
  33. 2026Supervised Guidance Training for Infinite-Dimensional Diffusion Modelscited by 3
  34. 2025Local MAP Sampling for Diffusion Modelscited by 2
  35. 2026Diffusion Path Samplers via Sequential Monte Carlocited by 2
  36. 2026Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixturescited by 2
  37. 2024Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Modelscited by 1
  38. 2025Measurement-Aligned Sampling for Inverse Problemcited by 1

50 most cited of 63 All 63 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models
  2. 2022From Denoising Diffusions to Denoising Markov Models
  3. 2020Denoising Diffusion Implicit Models
  4. 2024New algorithms for sampling and diffusion models
  5. 2025Diffusion Models: A Mathematical Introduction
  6. 2026Training-Free Generative Sampling via Moment-Matched Score Smoothing
  7. 2025Low-dimensional adaptation of diffusion models: Convergence in total variation
  8. 2022Denoising MCMC for Accelerating Diffusion-Based Generative Models