Research map / Probabilistic and scientific modeling / Dynamical systems
Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems
Ainesh Bakshi, Allen Liu, Ankur Moitra, morris yau
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use sixth-moment tensor decomposition followed by Ho-Kalman recovery | Mixtures of linear dynamical systems · Mixtures of linear dynamical systems | parameter estimation error: ≤ ε | Improved |
| Use sixth-moment tensor decomposition followed by Ho-Kalman recovery | Mixtures of linear dynamical systems · Partially observed mixtures of LDSs | trajectory length: ℓ ≥ 6(s+1) | Improved |
| Recover parameters and compute component posteriors | Fully observed mixtures of LDSs (C_i = I) · Trajectories of length l ≤ O(s) | posterior total variation distance: δ | Improved |
| Require joint non-degeneracy rather than strong distributional separation | Tensor decomposition + Ho-Kalman · Mixtures of linear dynamical systems | parameter recovery | Improved |
Closest papers by meaning
- Learning Mixtures of Linear Dynamical Systems (ICML 2022 · similarity 0.90)
- Functional Complexity-adaptive Temporal Tensor Decomposition (NeurIPS 2025 · similarity 0.87)
- Learning invariant representations of time-homogeneous stochastic dynamical systems (ICLR 2024 · similarity 0.86)
- Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data (ICLR 2025 · similarity 0.86)
- Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning (NeurIPS 2025 · similarity 0.86)
- Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
