Research map / Probabilistic and scientific modeling / Dynamical systems
Learning Dynamics Models with Stable Invariant Sets
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 |
|---|---|---|---|
| Constrain the learned dynamics to have a stable limit cycle | Dynamics model · Limit-cycle example | long-term prediction error | Helped |
| Use a stable invariant-set model trained on off-attractor data | Fluid flow dynamics model · Fluid flow prediction | long-term on-attractor prediction fidelity | Helped |
| Remove the learnable feature transform (ablation) | Proposed dynamics model · Van der Pol oscillator | limit-cycle shape fidelity | Hurt |
| Use a learnable stable invariant-set model instead of a vanilla model | Dynamics model · Van der Pol oscillator | long-term prediction error | Helped |
Closest papers by meaning
- DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems (ICML 2024 · similarity 0.88)
- Learning invariant representations of time-homogeneous stochastic dynamical systems (ICLR 2024 · similarity 0.85)
- When are dynamical systems learned from time series data statistically accurate? (NeurIPS 2024 · similarity 0.85)
- Learning Deep Dissipative Dynamics (AAAI 2025 · similarity 0.85)
- Neural Contractive Dynamical Systems (ICLR 2024 · similarity 0.85)
- Stable Port-Hamiltonian Neural Networks (NeurIPS 2025 · 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.