Research map / Probabilistic and scientific modeling / Dynamical systems
Lie-Algebraic Acceleration of Neural Koopman Dynamics
Jongwon Lee, Jiwoong Kim, Jungwoo Park, Sungwoo Park
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 Lie-algebraic parallel-scan Koopman model instead of Koopa | Neural Koopman dynamics · Met-Enkephalin | best MSE: 2.17×10−1 -> 7.54×10−2 | Improved |
| Heisenberg algebra variant vs unitary variant | Lie-algebraic Koopman · Met-Enkephalin | best MSE: 7.54×10−2 vs 1.13×10−1 | Mixed |
| replace GeoTDM with parallel-scan Lie model | Lie-algebraic Koopman · Met-Enkephalin | inference time (s): 1.38×102 -> 6.36×10−3 | Improved |
| replace KoVAE with Lie model on short chain | Lie-algebraic Koopman · Alkane short chain (C2-C3) | best MSE: 5.72×10−2 -> 7.27×10−2 | Hurt |
| replace GeoTDM with Lie model on long chain | Lie-algebraic Koopman · Alkane long chain (C7-C9) | best MSE: 5.41×10−2 -> 4.66×10−2 | Mixed |
| increase horizon from M=100 to M=1600 (16x) (ablation) | Lie-algebraic Koopman · Lotka-Volterra | inference time: runtime grows only 6.13× | Improved |
| use parallel scan for long horizons (ablation) | Lie-algebraic Koopman · Lotka-Volterra | max horizon: up to 1.45 × 106 timesteps | Improved |
Closest papers by meaning
- Lie Generator Networks for Nonlinear Partial Differential Equations (NeurIPS 2026 · similarity 0.89)
- Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics (NeurIPS 2026 · similarity 0.87)
- ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals (ICML 2025 · similarity 0.86)
- Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions (NeurIPS 2025 · similarity 0.85)
- Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems (NeurIPS 2025 · similarity 0.84)
- KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis (ICML 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.
