Research map / Learning theory and algorithms / Sample complexity
Learning Linear Dynamical Systems via Spectral Filtering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 wave-filtering rather than EM or SSID | System identification on the ill-conditioned SISO system · Synthetic SISO, ill-conditioned | prediction quality | Helped |
| Use wave-filtering rather than EM or SSID | System identification on the high-dimensional MIMO system · Synthetic MIMO, high-dimensional | prediction quality | Helped |
| Use wave-filtering on a nonlinear, non-symmetric system | Wave-filtering · Forced pendulum | prediction quality | Helped |
| Replace the traditional system-identification pipeline with wave-filtering | System identification on the synthetic examples · Synthetic systems | runtime: > 1000 times faster | Helped |
Closest papers by meaning
- A Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems (NeurIPS 2026 · similarity 0.89)
- SpectraLDS: Provable Distillation for Linear Dynamical Systems (NeurIPS 2025 · similarity 0.88)
- Efficient Spectral Control of Partially Observed Linear Dynamical Systems (NeurIPS 2025 · similarity 0.88)
- Learning invariant representations of time-homogeneous stochastic dynamical systems (ICLR 2024 · similarity 0.88)
- Universal Sequence Preconditioning (NeurIPS 2025 · similarity 0.87)
- Learning to Discover Iterative Spectral Algorithms (NeurIPS 2026 · similarity 0.87)
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.