mlsanityData to 14 Oct 2026

Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data

arXiv 1605.06432 ↗First posted 20 May 2016stat.ML cs.LG cs.SYcited by 156

Not on the map. Why?

Abstract (arXiv)

We introduce Deep Variational Bayes Filters (DVBF), a new method for unsupervised learning and identification of latent Markovian state space models. Leveraging recent advances in Stochastic Gradient Variational Bayes, DVBF can overcome intractable inference distributions via variational inference. Thus, it can handle highly nonlinear input data with temporal and spatial dependencies such as image sequences without domain knowledge. Our experiments show that enabling backpropagation through transitions enforces state space assumptions and significantly improves information content of the latent embedding. This also enables realistic long-term prediction.

Key facts. Cited by 156 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 38; 2022: 38; 2023: 19; 2024: 22; 2025: 14; 2026: 25.

156 papers.

Sort:

By area:

  1. 2021KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamicscited by 132
  2. 2021Pathdreamer: A World Model for Indoor Navigationcited by 118
  3. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 103
  4. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 85
  5. 2023For SALE: State-Action Representation Learning for Deep Reinforcement Learningcited by 75
  6. 2022Temporally Disentangled Representation Learningcited by 61
  7. 2021Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modelingcited by 59
  8. 2022StretchBEV: Stretching Future Instance Prediction Spatially and Temporallycited by 47
  9. 2021Causal Inference for Time series Analysis: Problems, Methods and Evaluationcited by 42
  10. 2021Clockwork Variational Autoencoderscited by 42
  11. 2021Visual Adversarial Imitation Learning using Variational Modelscited by 42
  12. 2025Towards General-Purpose Model-Free Reinforcement Learningcited by 41
38 more
  1. 2023Deep networks for system identification: a Surveycited by 37
  2. 2022Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systemscited by 36
  3. 2021From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligencecited by 35
  4. 2021Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filteringcited by 31
  5. 2021Action-Sufficient State Representation Learning for Control with Structural Constraintscited by 31
  6. 2021Which Mutual-Information Representation Learning Objectives are Sufficient for Control?cited by 29
  7. 2023Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Seriescited by 29
  8. 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatchcited by 25
  9. 2023DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setupcited by 19
  10. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  11. 2021Unsupervised Learned Kalman Filteringcited by 17
  12. 2022Latent Neural ODEs with Sparse Bayesian Multiple Shootingcited by 17
  13. 2021RNN with Particle Flow for Probabilistic Spatio-temporal Forecastingcited by 16
  14. 2022Flow-based Recurrent Belief State Learning for POMDPscited by 16
  15. 2022An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Contextcited by 15
  16. 2021Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Modelscited by 14
  17. 2021High-Accuracy Model-Based Reinforcement Learning, a Surveycited by 13
  18. 2022Latent State Marginalization as a Low-cost Approach for Improving Explorationcited by 13
  19. 2022On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learningcited by 13
  20. 2023Reward-Free Curricula for Training Robust World Modelscited by 13
  21. 2021Physics-aware, probabilistic model order reduction with guaranteed stabilitycited by 12
  22. 2021Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertaintycited by 11
  23. 2021Information is Power: Intrinsic Control via Information Capturecited by 11
  24. 2023Revisiting Structured Variational Autoencoderscited by 11
  25. 2025Closing the Train-Test Gap in World Models for Gradient-Based Planningcited by 11
  26. 2021Learning to Assimilate in Chaotic Dynamical Systemscited by 10
  27. 2024R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Modelscited by 10
  28. 2021Automatic variational inference with cascading flowscited by 9
  29. 2024KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertaintycited by 9
  30. 2025Probabilistic Forecasting via Autoregressive Flow Matchingcited by 9
  31. 2025MOBODY: Model Based Off-Dynamics Offline Reinforcement Learningcited by 9
  32. 2021GATSBI: Generative Agent-centric Spatio-temporal Object Interactioncited by 8
  33. 2022Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarioscited by 8
  34. 2022Neural Extended Kalman Filters for Learning and Predicting Dynamics of Structural Systemscited by 8
  35. 2022Learning Robust Dynamics through Variational Sparse Gatingcited by 8
  36. 2022Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulationcited by 8
  37. 2023Multi Time Scale World Modelscited by 8
  38. 2024Meta-Dynamical State Space Models for Integrative Neural Data Analysiscited by 8

50 most cited of 156 All 156 (JSON)