Research map / Probabilistic and scientific modeling / Dynamical systems
Multi-view Matrix Factorization for Linear Dynamical System Estimation
Mahdi Karami, Martha White, Dale Schuurmans, Csaba Szepesvari
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 |
|---|---|---|---|
| LDS-MV instead of N4SID | LDS estimation · ATL (Long) | NMSE: 0.52 -> 0.45 | Improved |
| LDS-MV instead of N4SID | LDS estimation · CAC (Short) | NMSE: 0.84 -> 0.63 | Improved |
| LDS-MV instead of N4SID | LDS estimation · ATL (Long) | runtime (CPU s): 2.34 -> 0.26 | Improved |
| LDS-MV instead of EM | LDS estimation · CAC (Short) | NMSE: 1.02 -> 0.63 | Improved |
| LDS-MV instead of N4SID on marginally stable system | LDS estimation · Synthetic S2 d=5 k=3 | NMSE: 0.42 -> 0.17 | Improved |
| LDS-MV instead of N4SID on easy system | LDS estimation · Synthetic S1 d=5 k=3 | NMSE: 0.12 -> 0.12 | No clear effect |
| LDS-MV instead of EM | LDS estimation · Synthetic S2 d=8 k=6 | NMSE: 0.04 -> 0.04 | No clear effect |
| LDS-MV instead of EM | LDS estimation · Synthetic S2 d=5 k=3 | NMSE: 0.15 -> 0.17 | Mixed |
| increase training sequence length (ablation) | LDS-MV vs N4SID · Synthetic S1 n=8 m=6 | NMSE | No clear effect |
| shorter training length (ablation) | LDS-MV vs N4SID · Synthetic S1 n=8 m=6 | NMSE | Improved |
| harder problems with higher MSE | LDS-MV vs N4SID · CAC time series | MSE | Improved |
Closest papers by meaning
- Gradient Descent Learns Linear Dynamical Systems (JMLR 2018 · similarity 0.87)
- Finite Time LTI System Identification (JMLR 2021 · similarity 0.87)
- Identifying latent state transitions in non-linear dynamical systems (ICLR 2025 · similarity 0.86)
- Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds (ICML 2024 · similarity 0.85)
- Momentum Particle Maximum Likelihood (ICML 2024 · similarity 0.85)
- Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control (NeurIPS 2025 · similarity 0.84)
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.
