mlsanityData to 7 Oct 2026

Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems

arXiv 1910.09588 ↗First posted 21 Oct 2019cs.LG stat.MLcited by 26

Not on the map. Why?

Abstract (arXiv)

We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for the continuous latent variables, while performing exact marginalization of the discrete latent variables. This allows us to use the reparameterization trick, and apply end-to-end training with stochastic gradient descent. We show that the proposed method can successfully segment time series data, including videos and 3D human pose, into meaningful ``regimes'' by using the piece-wise nonlinear dynamics.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 5; 2024: 7; 2025: 3; 2026: 4.

26 papers.

Sort:

By area:

  1. 2023Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Seriescited by 28
  2. 2022Learning Options via Compressioncited by 22
  3. 2021Deep Explicit Duration Switching Models for Time Seriescited by 17
  4. 2023Graph Switching Dynamical Systemscited by 10
  5. 2021Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report)cited by 9
  6. 2022Reinforcement Learning in Presence of Discrete Markovian Context Evolutioncited by 9
  7. 2023On the Identifiability of Switching Dynamical Systemscited by 9
  8. 2024Self-supervised contrastive learning performs non-linear system identificationcited by 9
  9. 2022Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarioscited by 8
  10. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  11. 2025Conformal Prediction for Time-series Forecasting with Change Pointscited by 4
  12. 2026TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learningcited by 4
14 more
  1. 2021Segmenting Hybrid Trajectories using Latent ODEscited by 3
  2. 2023T-SaS: Toward Shift-aware Dynamic Adaptation for Streaming Datacited by 3
  3. 2025Maximum Likelihood Learning of Latent Dynamics Without Reconstructioncited by 3
  4. 2024Amortized Equation Discovery in Hybrid Dynamical Systemscited by 2
  5. 2024Discovering group dynamics in coordinated time series via hierarchical recurrent switching-state modelscited by 1
  6. 2024A study of animal action segmentation algorithms across supervised, unsupervised, and semi-supervised learning paradigmscited by 1
  7. 2026End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systemscited by 1
  8. 2021Switching Recurrent Kalman Networkscited by 0
  9. 2023Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guaranteescited by 0
  10. 2024Long Range Switching Time Series Prediction via State Space Modelcited by 0
  11. 2024The Recurrent Sticky Hierarchical Dirichlet Process Hidden Markov Modelcited by 0
  12. 2024Bayesian Inference in Recurrent Explicit Duration Switching Linear Dynamical Systemscited by 0
  13. 2026Deep ZakaiJ: Structured Filtering for Jump-Diffusion Time Series Forecastingcited by 0
  14. 2026A note on goal-based hierarchical RLcited by 0