# Switching Linear Dynamics for Variational Bayes Filtering

arXiv: https://arxiv.org/abs/1905.12434 · HTML: https://mlsanity.com/paper/1905.12434/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2019.

## Built on by (most cited first, 17 of 17)

- [Deep Explicit Duration Switching Models for Time Series](https://mlsanity.com/paper/2110.13878/) (2021)
- [Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models](https://mlsanity.com/paper/2101.07046/) (2021)
- [On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2210.09256/) (2022)
- [HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling](https://mlsanity.com/paper/2110.02344/) (2021)
- [Reinforcement Learning in Presence of Discrete Markovian Context Evolution](https://mlsanity.com/paper/2202.06557/) (2022)
- [KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty](https://mlsanity.com/paper/2406.15131/) (2024)
- [Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios](https://mlsanity.com/paper/2206.14697/) (2022)
- [VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts](https://mlsanity.com/paper/2103.07292/) (2021)
- [Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models](https://mlsanity.com/paper/2312.02019/) (2023)
- [Compete and Compose: Learning Independent Mechanisms for Modular World Models](https://mlsanity.com/paper/2404.15109/) (2024)
- [Model-Based Reinforcement Learning via Stochastic Hybrid Models](https://mlsanity.com/paper/2111.06211/) (2021)
- [Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models](https://mlsanity.com/paper/2404.18896/) (2024)
- [Learning Reactive and Predictive Differentiable Controllers for Switching Linear Dynamical Models](https://mlsanity.com/paper/2103.14256/) (2021)
- [Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion](https://mlsanity.com/paper/2106.10393/) (2021)
- [PRRS Outbreak Prediction via Deep Switching Auto-Regressive Factorization Modeling](https://mlsanity.com/paper/2110.03147/) (2021)
- [End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems](https://mlsanity.com/paper/2605.06315/) (2026)
- [Switching Recurrent Kalman Networks](https://mlsanity.com/paper/2111.08291/) (2021)

## Abstract (arXiv)

System identification of complex and nonlinear systems is a central problem for model predictive control and model-based reinforcement learning. Despite their complexity, such systems can often be approximated well by a set of linear dynamical systems if broken into appropriate subsequences. This mechanism not only helps us find good approximations of dynamics, but also gives us deeper insight into the underlying system. Leveraging Bayesian inference, Variational Autoencoders and Concrete relaxations, we show how to learn a richer and more meaningful state space, e.g. encoding joint constraints and collisions with walls in a maze, from partial and high-dimensional observations. This representation translates into a gain of accuracy of learned dynamics showcased on various simulated tasks.