Research map / Probabilistic and scientific modeling / Dynamical systems
A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
Thibaut Germain, Rémi Flamary, Vladimir R Kostic, Karim Lounici
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 SGOT (spectral plus Grassmann OT) instead of spectral-only SOT or Grassmann-only GOT as KNN distance (ablation) | KNN classification of Koopman operators · 14 UEA multivariate time series datasets | accuracy | Improved |
| use SGOT instead of Hilbert-Schmidt operator distance | KNN classification of Koopman operators · 14 UEA datasets | accuracy | Improved |
| use SGOT instead of Hilbert-Schmidt or SOT distance under shifts of a linear oscillator | metric behavior · simulated oscillator frequency/decay/rank shifts | metric response | Improved |
| compare systems at different sampling frequencies with SGOT versus others | metric invariance · sampling frequency shift scenario | metric value stability | Improved |
| use SGOT barycenter instead of Hilbert-Schmidt barycenters for interpolation | Frechet mean of oscillator systems · interpolation of 1D linear oscillators | interpolation quality (qualitative) | Improved |
| add spectral decomposition constraints to the Hilbert-Schmidt barycenter (ablation) | Hilbert-Schmidt barycenter · interpolation of 1D linear oscillators | damping behavior (qualitative) | Mixed |
Closest papers by meaning
- ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals (ICML 2025 · similarity 0.88)
- Learning invariant representations of time-homogeneous stochastic dynamical systems (ICLR 2024 · similarity 0.87)
- KoopSTD: Reliable Similarity Analysis between Dynamical Systems via Approximating Koopman Spectrum with Timescale Decoupling (ICML 2025 · similarity 0.86)
- Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems (NeurIPS 2025 · similarity 0.86)
- Beyond DSA: Conjugacy-based Comparison of Dynamical Systems (NeurIPS 2026 · similarity 0.86)
- Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics (NeurIPS 2026 · similarity 0.85)
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.
