Research map / Time series / Causal and generative time series
Machine learning structure preserving brackets for forecasting irreversible processes
Kookjin Lee, Nathaniel Trask, Panos Stinis
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 |
|---|---|---|---|
| enforce degeneracy conditions exactly via GNODE parameterization instead of soft penalty (ablation) | GENERIC neural ODE · damped nonlinear oscillator | entropy production dS/dt >= 0 and extrapolation of H | Improved |
| GNODE vs black-box NODE for forecasting beyond training time | neural ODE · damped nonlinear oscillator and two gas containers | extrapolation accuracy | Improved |
| exact degeneracy conditions vs penalty (ablation) | GENERIC neural ODE · two gas containers | forecasting and second law compliance | Improved |
| use learned GNODE brackets in thermally forced SDE (fluctuation-dissipation) | GNODE · stochastic damped oscillator | std of q, p at T=80: std q 9.9684e-6 vs 1.6436e-6; std p 3.1971e-5 vs 3.2972e-6 | Mixed |
Closest papers by meaning
- Learning Deep Dissipative Dynamics (AAAI 2025 · similarity 0.86)
- Learning invariant representations of time-homogeneous stochastic dynamical systems (ICLR 2024 · similarity 0.86)
- Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling (NeurIPS 2024 · similarity 0.86)
- DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems (ICML 2024 · similarity 0.85)
- HHD-GP: Incorporating Helmholtz-Hodge Decomposition into Gaussian Processes for Learning Dynamical Systems (NeurIPS 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.
