mlsanityData to 7 Oct 2026

Differentiable Particle Filtering via Entropy-Regularized Optimal Transport

arXiv 2102.07850 ↗First posted 15 Feb 2021stat.ML cs.LG stat.COcited by 59

Not on the map. Why?

Abstract (arXiv)

Particle Filtering (PF) methods are an established class of procedures for performing inference in non-linear state-space models. Resampling is a key ingredient of PF, necessary to obtain low variance likelihood and states estimates. However, traditional resampling methods result in PF-based loss functions being non-differentiable with respect to model and PF parameters. In a variational inference context, resampling also yields high variance gradient estimates of the PF-based evidence lower bound. By leveraging optimal transport ideas, we introduce a principled differentiable particle filter and provide convergence results. We demonstrate this novel method on a variety of applications.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 32 of its 63 references that are in the map. First posted on arXiv 15 Feb 2021.

Builds on

32 of 63 references.

References · 32

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  3. 2018Computational Optimal Transportcited by 765
  4. 2015Importance Weighted Autoencoderscited by 454
  5. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  6. 2017Learning Generative Models with Sinkhorn Divergencescited by 310
  7. 2017Near-linear time approximation algorithms for optimal transport via Sinkhorn iterationcited by 219
  8. 2013Fast Computation of Wasserstein Barycenterscited by 216
  9. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
  10. 2017Large-Scale Optimal Transport and Mapping Estimationcited by 120
  11. 2017TensorFlow Distributionscited by 105
  12. 2017Variational Sequential Monte Carlocited by 93
20 more
  1. 2017Filtering Variational Objectivescited by 91
  2. 2017Auto-Encoding Sequential Monte Carlocited by 64
  3. 2018Particle Filter Networks with Application to Visual Localizationcited by 64
  4. 2018An Introduction to Probabilistic Programmingcited by 62
  5. 2018Differentiable Particle Filters: End-to-End Learning with Algorithmic Priorscited by 58
  6. 2014On Particle Methods for Parameter Estimation in State-Space Modelscited by 47
  7. 2018Massively scalable Sinkhorn distances via the Nystr"om methodcited by 40
  8. 2019Particle Filter Recurrent Neural Networkscited by 36
  9. 2015Black box variational inference for state space modelscited by 31
  10. 2020Discriminative Particle Filter Reinforcement Learning for Complex Partial Observationscited by 27
  11. 2016Wasserstein Discriminant Analysiscited by 25
  12. 2018An explicit analysis of the entropic penalty in linear programmingcited by 23
  13. 2020How to Train Your Differentiable Filtercited by 23
  14. 2020Towards Differentiable Resamplingcited by 19
  15. 2020Linear Time Sinkhorn Divergences using Positive Featurescited by 17
  16. 2016Stochastic Backpropagation through Mixture Density Distributionscited by 14
  17. 2020End-To-End Semi-supervised Learning for Differentiable Particle Filterscited by 12
  18. 2018Tensor Monte Carlo: particle methods for the GPU eracited by 8
  19. 2019Sequential Ensemble Transform for Bayesian Inverse Problemscited by 4
  20. 2018Scalable Bayesian Learning for State Space Models using Variational Inference with SMC Samplerscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 7; 2023: 11; 2024: 13; 2025: 12; 2026: 7.

59 papers.

Sort:

By area:

  1. 2022Continual Repeated Annealed Flow Transport Monte Carlocited by 66
  2. 2021Differentiable SLAM-net: Learning Particle SLAM for Visual Navigationcited by 34
  3. 2021Auto-differentiable Ensemble Kalman Filterscited by 28
  4. 2022Automatic Differentiation of Programs with Discrete Randomnesscited by 28
  5. 2023An overview of differentiable particle filters for data-adaptive sequential Bayesian inferencecited by 23
  6. 2021Online Variational Filtering and Parameter Learningcited by 19
  7. 2021Differentiable Particle Filtering without Modifying the Forward Passcited by 18
  8. 2021Differentiable Particle Filters through Conditional Normalizing Flowcited by 15
  9. 2022Rethinking Initialization of the Sinkhorn Algorithmcited by 14
  10. 2023Reduced-Order Autodifferentiable Ensemble Kalman Filterscited by 12
  11. 2021Quantitative Uniform Stability of the Iterative Proportional Fitting Procedurecited by 11
  12. 2024Normalizing Flow-based Differentiable Particle Filterscited by 10
38 more
  1. 2021Efficient Learning of the Parameters of Non-Linear Models using Differentiable Resampling in Particle Filterscited by 9
  2. 2023Transport with Support: Data-Conditional Diffusion Bridgescited by 9
  3. 2021Compositional Learning-based Planning for Vision POMDPscited by 8
  4. 2023Unsupervised Learning of Sampling Distributions for Particle Filterscited by 8
  5. 2021Variational Marginal Particle Filterscited by 6
  6. 2022Conditional Measurement Density Estimation in Sequential Monte Carlo via Normalizing Flowcited by 6
  7. 2023Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Frameworkcited by 6
  8. 2022Phi-DVAE: Physics-Informed Dynamical Variational Autoencoders for Unstructured Data Assimilationcited by 4
  9. 2023Sparse Graphical Linear Dynamical Systemscited by 4
  10. 2023On Feynman--Kac training of partial Bayesian neural networkscited by 4
  11. 2024Enhanced SMC2: Leveraging Gradient Information from Differentiable Particle Filters Within Langevin Proposalscited by 4
  12. 2025Learning to be Smooth: An End-to-End Differentiable Particle Smoothercited by 4
  13. 2022Particle-Based Score Estimation for State Space Model Learning in Autonomous Drivingcited by 3
  14. 2022De-Sequentialized Monte Carlo: a parallel-in-time particle smoothercited by 2
  15. 2023Differentiable Bootstrap Particle Filters for Regime-Switching Modelscited by 2
  16. 2023Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplerscited by 2
  17. 2023Learning Differentiable Particle Filter on the Flycited by 2
  18. 2023Risk-Sensitive Stochastic Optimal Control as Rao-Blackwellized Markovian Score Climbingcited by 2
  19. 2024Differentiable and Stable Long-Range Tracking of Multiple Posterior Modescited by 2
  20. 2024Resampling-free Particle Filters in High-dimensionscited by 2
  21. 2024Revisiting semi-supervised training objectives for differentiable particle filterscited by 2
  22. 2024Regime Learning for Differentiable Particle Filterscited by 2
  23. 2025Deep Variational Sequential Monte Carlo for High-Dimensional Observationscited by 2
  24. 2025Sequential Monte Carlo for Policy Optimization in Continuous POMDPscited by 2
  25. 2025Schr"odinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentrescited by 2
  26. 2025DiffPF: Differentiable Particle Filtering with Generative Sampling via Conditional Diffusion Modelscited by 2
  27. 2025PyDPF: A Python Package for Differentiable Particle Filteringcited by 2
  28. 2025Diffusion differentiable resamplingcited by 2
  29. 2024Differentiable Cost-Parameterized Monge Map Estimatorscited by 1
  30. 2024Permutation Invariant Learning with High-Dimensional Particle Filterscited by 1
  31. 2024Nonparametric Filtering, Estimation and Classification using Neural Jump ODEscited by 1
  32. 2025DnD Filter: Differentiable State Estimation for Dynamic Systems using Diffusion Modelscited by 1
  33. 2025Hess-MC2: Sequential Monte Carlo Squared using Hessian Information and Second Order Proposalscited by 1
  34. 2024Differentiable Particle Filtering using Optimal Placement Resamplingcited by 0
  35. 2024Accelerated Inference for Partially Observed Markov Processes using Automatic Differentiationcited by 0
  36. 2024Inverse Particle Filtercited by 0
  37. 2024Learning state and proposal dynamics in state-space models using differentiable particle filters and neural networkscited by 0
  38. 2025Meta-reinforcement learning with minimum attentioncited by 0

50 most cited of 59 All 59 (JSON)