mlsanityData to 7 Oct 2026

Conditional Measurement Density Estimation in Sequential Monte Carlo via Normalizing Flow

arXiv 2203.08617 ↗First posted 16 Mar 2022cs.AI cs.CV cs.ROcited by 6

Not on the map. Why?

Abstract (arXiv)

Tuning of measurement models is challenging in real-world applications of sequential Monte Carlo methods. Recent advances in differentiable particle filters have led to various efforts to learn measurement models through neural networks. But existing approaches in the differentiable particle filter framework do not admit valid probability densities in constructing measurement models, leading to incorrect quantification of the measurement uncertainty given state information. We propose to learn expressive and valid probability densities in measurement models through conditional normalizing flows, to capture the complex likelihood of measurements given states. We show that the proposed approach leads to improved estimation performance and faster training convergence in a visual tracking experiment.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

18 of 25 references.

References · 18

  1. 2016Density estimation using Real NVPcited by 2,029
  2. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  3. 2017A Distributional Perspective on Reinforcement Learningcited by 743
  4. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  5. 2019Noise Flow: Noise Modeling with Conditional Normalizing Flowscited by 108
  6. 2018Particle Filter Networks with Application to Visual Localizationcited by 64
  7. 2021Differentiable Particle Filtering via Entropy-Regularized Optimal Transportcited by 59
  8. 2018Differentiable Particle Filters: End-to-End Learning with Algorithmic Priorscited by 58
  9. 2018Conditional Density Estimation with Bayesian Normalising Flowscited by 54
  10. 2014On Particle Methods for Parameter Estimation in State-Space Modelscited by 47
  11. 2016Backprop KF: Learning Discriminative Deterministic State Estimatorscited by 47
  12. 2019Structured Output Learning with Conditional Generative Flowscited by 37
6 more
  1. 2020How to Train Your Differentiable Filtercited by 23
  2. 2018Gaussian Process Conditional Density Estimationcited by 22
  3. 2021Differentiable Particle Filters through Conditional Normalizing Flowcited by 15
  4. 2017The Kernel Mixture Network: A Nonparametric Method for Conditional Density Estimation of Continuous Random Variablescited by 14
  5. 2020End-To-End Semi-supervised Learning for Differentiable Particle Filterscited by 12
  6. 2016Bottleneck Conditional Density Estimationcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3.

6 papers.

  1. 2023An overview of differentiable particle filters for data-adaptive sequential Bayesian inferencecited by 23
  2. 2024Normalizing Flow-based Differentiable Particle Filterscited by 10
  3. 2023Differentiable Bootstrap Particle Filters for Regime-Switching Modelscited by 2
  4. 2023Learning Differentiable Particle Filter on the Flycited by 2
  5. 2024Revisiting semi-supervised training objectives for differentiable particle filterscited by 2
  6. 2024Inverse Particle Filtercited by 0