mlsanityData to 7 Oct 2026

Recurrent switching linear dynamical systems

arXiv 1610.08466 ↗First posted 26 Oct 2016stat.MLcited by 34

Not on the map. Why?

Abstract (arXiv)

Many natural systems, such as neurons firing in the brain or basketball teams traversing a court, give rise to time series data with complex, nonlinear dynamics. We can gain insight into these systems by decomposing the data into segments that are each explained by simpler dynamic units. Building on switching linear dynamical systems (SLDS), we present a new model class that not only discovers these dynamical units, but also explains how their switching behavior depends on observations or continuous latent states. These "recurrent" switching linear dynamical systems provide further insight by discovering the conditions under which each unit is deployed, something that traditional SLDS models fail to do. We leverage recent algorithmic advances in approximate inference to make Bayesian inference in these models easy, fast, and scalable.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 4; 2024: 10; 2025: 8; 2026: 5.

34 papers.

Sort:

By area:

  1. 2022Is a Modular Architecture Enough?cited by 35
  2. 2024Out-of-Domain Generalization in Dynamical Systems Reconstructioncited by 33
  3. 2022Learning Options via Compressioncited by 22
  4. 2023Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysiscited by 21
  5. 2024Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstructioncited by 18
  6. 2021Deep Explicit Duration Switching Models for Time Seriescited by 17
  7. 2022Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamicscited by 16
  8. 2023Graph Switching Dynamical Systemscited by 10
  9. 2023On the Identifiability of Switching Dynamical Systemscited by 9
  10. 2024A scalable generative model for dynamical system reconstruction from neuroimaging datacited by 9
  11. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  12. 2024Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamicscited by 6
22 more
  1. 2025Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviorscited by 6
  2. 2025POCO: Scalable Neural Forecasting through Population Conditioningcited by 6
  3. 2023SiBBlInGS: Similarity-driven Building-Block Inference using Graphs across Statescited by 5
  4. 2024Navigation under uncertainty: Trajectory prediction and occlusion reasoning with switching dynamical systemscited by 4
  5. 2025Uncovering the Computational Roles of Nonlinearity in Sequence Modeling Using Almost-Linear RNNscited by 4
  6. 2025Conformal Prediction for Time-series Forecasting with Change Pointscited by 4
  7. 2026Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Modelscited by 4
  8. 2021Segmenting Hybrid Trajectories using Latent ODEscited by 3
  9. 2025AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Modelscited by 3
  10. 2025Detecting Invariant Manifolds in ReLU-Based RNNscited by 3
  11. 2026Continuous-Time Piecewise-Linear Recurrent Neural Networkscited by 3
  12. 2026Position: A Dynamical Systems Perspective is Needed to Advance Time Series Modelingcited by 3
  13. 2021Learning Reactive and Predictive Differentiable Controllers for Switching Linear Dynamical Modelscited by 1
  14. 2024LINOCS: Lookahead Inference of Networked Operators for Continuous Stabilitycited by 1
  15. 2024A study of animal action segmentation algorithms across supervised, unsupervised, and semi-supervised learning paradigmscited by 1
  16. 2022Parameter-varying neural ordinary differential equations with partition-of-unity networkscited by 0
  17. 2024Long Range Switching Time Series Prediction via State Space Modelcited by 0
  18. 2024Hybrid Recurrent Models Support Emergent Descriptions for Hierarchical Planning and Controlcited by 0
  19. 2024Learning in Hybrid Active Inference Modelscited by 0
  20. 2025Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamicscited by 0
  21. 2026Behavior-dLDS: A decomposed linear dynamical systems model for neural activity partially constrained by behaviorcited by 0
  22. 2026CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Datacited by 0