mlsanityData to 7 Oct 2026

Diffusion differentiable resampling

arXiv 2512.10401 ↗First posted 11 Dec 2025stat.ML cs.LG math.STcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper is concerned with differentiable resampling in the context of sequential Monte Carlo (e.g., particle filtering). Drawing on reparametrisation, we propose a new resampling method that is informative and instantly differentiable, based on a training-free diffusion model surrogate. We theoretically prove that our diffusion resampling method provides a consistent resampling distribution, and we show empirically that it outperforms the state-of-the-art differentiable resampling methods on multiple filtering and parameter estimation benchmarks. Finally, we show that it achieves competitive end-to-end performance when used in learning a complex dynamics-decoder model with high-dimensional image observations.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 49 of its 86 references that are in the map. First posted on arXiv 11 Dec 2025.

Builds on

49 of 86 references.

References · 49

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  4. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  5. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  6. 2019Hamiltonian Neural Networkscited by 702
  7. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  8. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 526
  9. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptionscited by 440
  10. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  11. 2020WeatherBench: A benchmark dataset for data-driven weather forecastingcited by 272
  12. 2020Scalable Gradients for Stochastic Differential Equationscited by 264
37 more
  1. 2022On Neural Differential Equationscited by 264
  2. 2022Convergence of denoising diffusion models under the manifold hypothesiscited by 237
  3. 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 206
  4. 2021Efficient and Modular Implicit Differentiationcited by 199
  5. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 182
  6. 2017Stein Variational Gradient Descent as Gradient Flowcited by 149
  7. 2022Optimal Transport Tools (OTT): A JAX Toolbox for all things Wassersteincited by 96
  8. 2017Variational Sequential Monte Carlocited by 93
  9. 2021Efficient and Accurate Gradients for Neural SDEscited by 68
  10. 2018Particle Filter Networks with Application to Visual Localizationcited by 64
  11. 2022Do Bayesian Neural Networks Need To Be Fully Stochastic?cited by 63
  12. 2021Differentiable Particle Filtering via Entropy-Regularized Optimal Transportcited by 59
  13. 2020Modeling Continuous Stochastic Processes with Dynamic Normalizing Flowscited by 37
  14. 2023An Ensemble Score Filter for Tracking High-Dimensional Nonlinear Dynamical Systemscited by 33
  15. 2022Automatic Differentiation of Programs with Discrete Randomnesscited by 28
  16. 2023An overview of differentiable particle filters for data-adaptive sequential Bayesian inferencecited by 23
  17. 2015An Overview on the Estimation of Large Covariance and Precision Matricescited by 20
  18. 2020Towards Differentiable Resamplingcited by 19
  19. 2025SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equationscited by 19
  20. 2021Differentiable Particle Filtering without Modifying the Forward Passcited by 18
  21. 2024Conditional sampling within generative diffusion modelscited by 18
  22. 2023Amortized Reparametrization: Efficient and Scalable Variational Inference for Latent SDEscited by 15
  23. 2024Conditioning non-linear and infinite-dimensional diffusion processescited by 15
  24. 2024Taming Diffusion Models for Image Restoration: A Reviewcited by 12
  25. 2024Conditioning diffusion models by explicit forward-backward bridgingcited by 11
  26. 2021Efficient Learning of the Parameters of Non-Linear Models using Differentiable Resampling in Particle Filterscited by 9
  27. 2023Improved Rate of First Order Algorithms for Entropic Optimal Transportcited by 7
  28. 2021Variational Marginal Particle Filterscited by 6
  29. 2019Analysis of the BFGS Method with Errorscited by 5
  30. 2022On resampling schemes for particle filters with weakly informative observationscited by 5
  31. 2024Score matching for bridges without learning time-reversalscited by 5
  32. 2023On Feynman--Kac training of partial Bayesian neural networkscited by 4
  33. 2025Generative diffusion posterior sampling for informative likelihoodscited by 4
  34. 2025Dimension-free error estimate for diffusion model and optimal schedulingcited by 3
  35. 2025PyDPF: A Python Package for Differentiable Particle Filteringcited by 2
  36. 2023Stochastic filtering with moment representationcited by 1
  37. 2024Temperature Optimization for Bayesian Deep Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Categorical Reparameterization with Denoising Diffusion modelscited by 0
  2. 2026Efficient Learning of Deep State Space Models via Importance Smoothingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusing Differentiable Representations
  2. 2024Particle Denoising Diffusion Sampler
  3. 2023Correcting Diffusion Generation through Resampling
  4. 2024Diffusion Posterior Proximal Sampling for Image Restoration
  5. 2025Unifying and extending Diffusion Models through PDEs for solving Inverse Problems
  6. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality
  7. 2023Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise
  8. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency