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

arXiv: https://arxiv.org/abs/1605.06432 · HTML: https://mlsanity.com/paper/1605.06432/

## Key facts

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

## Built on by (most cited first, 30 of 156)

- [KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics](https://mlsanity.com/paper/2107.10043/) (2021)
- [Pathdreamer: A World Model for Indoor Navigation](https://mlsanity.com/paper/2105.08756/) (2021)
- [Modeling Irregular Time Series with Continuous Recurrent Units](https://mlsanity.com/paper/2111.11344/) (2021)
- [DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation](https://mlsanity.com/paper/2308.07498/) (2023)
- [For SALE: State-Action Representation Learning for Deep Reinforcement Learning](https://mlsanity.com/paper/2306.02451/) (2023)
- [Temporally Disentangled Representation Learning](https://mlsanity.com/paper/2210.13647/) (2022)
- [Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling](https://mlsanity.com/paper/2102.13156/) (2021)
- [StretchBEV: Stretching Future Instance Prediction Spatially and Temporally](https://mlsanity.com/paper/2203.13641/) (2022)
- [Causal Inference for Time series Analysis: Problems, Methods and Evaluation](https://mlsanity.com/paper/2102.05829/) (2021)
- [Clockwork Variational Autoencoders](https://mlsanity.com/paper/2102.09532/) (2021)
- [Visual Adversarial Imitation Learning using Variational Models](https://mlsanity.com/paper/2107.08829/) (2021)
- [Towards General-Purpose Model-Free Reinforcement Learning](https://mlsanity.com/paper/2501.16142/) (2025)
- [Deep networks for system identification: a Survey](https://mlsanity.com/paper/2301.12832/) (2023)
- [Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems](https://mlsanity.com/paper/2207.02542/) (2022)
- [From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence](https://mlsanity.com/paper/2110.15245/) (2021)
- [Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filtering](https://mlsanity.com/paper/2106.07992/) (2021)
- [Action-Sufficient State Representation Learning for Control with Structural Constraints](https://mlsanity.com/paper/2110.05721/) (2021)
- [Which Mutual-Information Representation Learning Objectives are Sufficient for Control?](https://mlsanity.com/paper/2106.07278/) (2021)
- [Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series](https://mlsanity.com/paper/2301.11308/) (2023)
- [Cross-Domain Policy Adaptation by Capturing Representation Mismatch](https://mlsanity.com/paper/2405.15369/) (2024)
- [DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setup](https://mlsanity.com/paper/2306.03897/) (2023)
- [Unsupervised Representation Learning in Deep Reinforcement Learning: A Review](https://mlsanity.com/paper/2208.14226/) (2022)
- [Unsupervised Learned Kalman Filtering](https://mlsanity.com/paper/2110.09005/) (2021)
- [Latent Neural ODEs with Sparse Bayesian Multiple Shooting](https://mlsanity.com/paper/2210.03466/) (2022)
- [RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting](https://mlsanity.com/paper/2106.06064/) (2021)
- [Flow-based Recurrent Belief State Learning for POMDPs](https://mlsanity.com/paper/2205.11051/) (2022)
- [An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context](https://mlsanity.com/paper/2212.12735/) (2022)
- [Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models](https://mlsanity.com/paper/2101.07046/) (2021)
- [High-Accuracy Model-Based Reinforcement Learning, a Survey](https://mlsanity.com/paper/2107.08241/) (2021)
- [Latent State Marginalization as a Low-cost Approach for Improving Exploration](https://mlsanity.com/paper/2210.00999/) (2022)

## 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.