mlsanityData to 7 Oct 2026

Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models

arXiv 2110.04738 ↗First posted 10 Oct 2021eess.SP cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from knowledge of the underlying statistics, however, deep learning based tracking systems struggle to reliably characterize uncertainty. In this paper, we investigate the ability of KalmanNet, a recently proposed hybrid model-based deep state tracking algorithm, to estimate an uncertainty measure. By exploiting the interpretable nature of KalmanNet, we show that the error covariance matrix can be computed based on its internal features, as an uncertainty measure. We demonstrate that when the system dynamics are known, KalmanNet-which learns its mapping from data without access to the statistics-provides uncertainty similar to that provided by the KF; and while in the presence of evolution model-mismatch, KalmanNet pro-vides a more accurate error estimation.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 12 of its 23 references that are in the map. First posted on arXiv 10 Oct 2021.

Builds on

12 of 23 references.

References · 12

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  3. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  4. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  5. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
  6. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 154
  7. 2020Model-Based Deep Learningcited by 136
  8. 2021KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamicscited by 128
  9. 2021Epistemic Neural Networkscited by 120
  10. 2017Variational Sequential Monte Carlocited by 93
  11. 2019Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spacescited by 64
  12. 2016Backprop KF: Learning Discriminative Deterministic State Estimatorscited by 47

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 0; 2025: 0; 2026: 2.

6 papers.

  1. 2022Model-Based Deep Learning: On the Intersection of Deep Learning and Optimizationcited by 50
  2. 2023GSP-KalmanNet: Tracking Graph Signals via Neural-Aided Kalman Filteringcited by 10
  3. 2022Outlier-Insensitive Kalman Filtering Using NUV Priorscited by 1
  4. 2022LQGNet: Hybrid Model-Based and Data-Driven Linear Quadratic Stochastic Controlcited by 0
  5. 2026Uncertainty-Aware Vision-based Risk Object Identification via Conformal Risk Tube Predictioncited by 0
  6. 2026Unscented KalmanNet: Structure-Preserving Deep Learning with Calibrated Posterior Uncertainty under Incomplete Physics and Unknown Noisecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Neural Kalman Filtering for Unknown Dynamics: Task-Aware Learning with a Koopman Backbone ↗
  2. 2024Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability
  3. 2025TrackDiffuser: Nearly Model-Free Bayesian Filtering with Diffusion Model
  4. 2025Neural Network State-Space Estimators ↗
  5. 2023Neural State-Space Models: Empirical Evaluation of Uncertainty Quantification
  6. 2024Outlier-robust Kalman Filtering through Generalised Bayes
  7. 2026Latent Matters: Learning Deep State-Space Models
  8. 2025DnD Filter: Differentiable State Estimation for Dynamic Systems using Diffusion Models