Research map / Learning theory and algorithms / Prediction and decision losses
Exact Verification of ReLU Neural Control Barrier Functions
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 |
|---|---|---|---|
| Use the proposed verifier instead of SMT-based dReal or Z3 | NCBF verification · Darboux | verification runtime: 0.43 vs 0.36; 2.02 vs >3hrs; 0.47 vs 7.70 and 15.81 | Mixed |
| Use the proposed verifier instead of SMT-based dReal or Z3 | NCBF verification · Obstacle Avoidance | verification runtime: 7.35 vs >6hrs; 185.07 vs >6hrs | Helped |
| Use the proposed verifier instead of SMT-based dReal or Z3 | NCBF verification · hi-ord8 | verification runtime: 3.72 vs >3hrs | Helped |
| Use the proposed verifier rather than dReal or Z3 | NCBF verification · Spacecraft Rendezvous | verification availability | Helped |
| Increase the number of neurons in the network | Proposed verifier · Darboux | verification runtime: 0.43 -> 108.44 | Hurt |
| Use a 32-neuron, one-hidden-layer NCBF instead of SOS Degree 10 | Obstacle Avoidance · Obstacle Avoidance | safe region volume: 19.99 -> 37.76 | Helped |
| Use SOS Degree 10 instead of a 32-neuron, one-hidden-layer NCBF | Obstacle Avoidance · Obstacle Avoidance | training time: 262.89s -> 551.31s | Hurt |
Closest papers by meaning
- SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions (NeurIPS 2024 · similarity 0.92)
- Verified Safe Reinforcement Learning for Neural Network Dynamic Models (NeurIPS 2024 · similarity 0.85)
- Provably Safe Neural Network Controllers via Differential Dynamic Logic (NeurIPS 2024 · similarity 0.84)
- Neural Control and Certificate Repair via Runtime Monitoring (AAAI 2025 · similarity 0.83)
- A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems (ICML 2025 · similarity 0.83)
- Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion (NeurIPS 2025 · similarity 0.82)
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.