Research map / Probabilistic and scientific modeling / Dynamical systems
Neural Abstractions
Alessandro Abate, Alec Edwards, Mirco Giacobbe
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 certified neural abstraction with SpaceEx instead of Flow* | Nonlinear dynamical models · Jet Engine, Steam Governor, Exponential, Water Tank, Non-Lipschitz 1, Non-Lipschitz 2 | safety verification | Mixed |
| Use Neural Abstractions + SpaceEx instead of Flow* | Jet Engine · Jet Engine | computation time: 1.3 vs 215 | Hurt |
| Use Neural Abstractions + SpaceEx instead of Flow* | Steam Governor · Steam Governor | computation time: 62 vs 219 | Hurt |
| Use Neural Abstractions + SpaceEx instead of Flow* | Exponential · Exponential | safety verification | Improved |
| Use Neural Abstractions + SpaceEx instead of Flow* | Exponential · Exponential | computation time: 1034 vs 308 | Improved |
| Use neural abstractions for models that Flow* cannot analyze | Nonlinear dynamical models · Water Tank, Non-Lipschitz 1, Non-Lipschitz 2 | safety verification | Improved |
| Use neural abstractions instead of affine simplicial meshes | Dynamical model abstraction · Jet Engine | approximation error bound: 1.33 -> 0.11 | Improved |
| Use neural abstractions instead of affine simplicial meshes | Dynamical model abstraction · Steam | approximation error bound: 3.58 -> 0.27 | Improved |
| Use neural abstractions instead of affine simplicial meshes | Dynamical model abstraction · Exponential | approximation error bound: 13.7 -> 0.29 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- Flow* — Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design (ICML 2019) · better on 1 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Verified Safe Reinforcement Learning for Neural Network Dynamic Models (NeurIPS 2024 · similarity 0.87)
- Neural Closure Certificates (AAAI 2024 · similarity 0.86)
- Provably Safe Neural Network Controllers via Differential Dynamic Logic (NeurIPS 2024 · similarity 0.85)
- Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction (NeurIPS 2024 · similarity 0.85)
- Stability Analysis of Switched Linear Systems with Neural Lyapunov Functions (AAAI 2024 · similarity 0.84)
- Analytical Lyapunov Function Discovery: An RL-based Generative Approach (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.
