Research map / Learning theory and algorithms / Combinatorial and search optimization
General Cutting Planes for Bound-Propagation-Based Neural Network Verification
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 |
|---|---|---|---|
| Add MIP-generated general cutting planes to bound propagation | GCP-CROWN with MIP cuts · oval21 | # verified: 11 -> 23 | Helped |
| Add MIP-generated general cutting planes to bound propagation | GCP-CROWN with MIP cuts · cifar10-resnet | # verified: 58 -> 63 | Helped |
| Add MIP-generated cuts and use GPU bound propagation | GCP-CROWN · oval20, CIFAR-10 Base | time(s): 118.23 -> 4.07 | Helped |
| Add MIP-generated cuts and use GPU bound propagation | GCP-CROWN · oval20, CIFAR-10 Wide | %timeout: 2.00 -> 0.00 | Helped |
| Add MIP-generated cuts to bound propagation | GCP-CROWN · oval21 hard properties | lower bound: 0.51 | Helped |
| Use cuts without branching | GCP-CROWN with MIP cuts · oval21 hard properties | properties verified: 4 out of 39 | Helped |
| Remove all cuts (set cut multipliers to zero) (ablation) | GCP-CROWN · general cutting-plane LP relaxation | lower bound | Hurt |
Closest papers by meaning
- Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes (NeurIPS 2024 · similarity 0.92)
- SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming (ICML 2025 · similarity 0.90)
- Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification (NeurIPS 2025 · similarity 0.89)
- Dynamic Back-Substitution in Bound-Propagation-Based Neural Network Verification (AAAI 2025 · similarity 0.89)
- Understanding Certified Training with Interval Bound Propagation (ICLR 2024 · similarity 0.85)
- DeepBern-Nets: Taming the Complexity of Certifying Neural Networks Using Bernstein Polynomial Activations and Precise Bound Propagation (AAAI 2024 · 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.