Research map / Probabilistic and scientific modeling / Dynamical systems
LUCID: Learning-Enabled Uncertainty-Aware Certification of Stochastic Dynamical Systems
Ernesto Casablanca, Oliver Schön, Paolo Zuliani, Sadegh Soudjani
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 a finer lattice and more frequencies for the LP relaxation | LUCID · Barr2, Barr3, Over benchmarks | runtime: 00:01 (linear) -> 93:56 (Over) | Hurt |
| sample the lattice denser than the Nyquist frequency (ablation) | LUCID LP relaxation · general | efficiency vs conservativeness | Mixed |
| increase set_scaling to enlarge X, X0, XU sets | LUCID · Linear running example | constraint tightening epsilon | Improved |
| compare LUCID certified bound to Monte Carlo point-wise estimates | LUCID · Barr2, Barr3, Over | safety probability: MC approx. 95-100% vs LUCID 51.63% to 63.17% | Mixed |
Closest papers by meaning
- Safely Learning Controlled Stochastic Dynamics (NeurIPS 2025 · similarity 0.88)
- Neural Continuous-Time Supermartingale Certificates (AAAI 2025 · similarity 0.87)
- A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems (ICML 2025 · similarity 0.86)
- Verified Safe Reinforcement Learning for Neural Network Dynamic Models (NeurIPS 2024 · similarity 0.85)
- The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling (NeurIPS 2026 · similarity 0.84)
- Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them) (ICML 2024 · 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.
