Research map / Learning theory and algorithms / Sample complexity
How hard is learning to cut? Trade-offs and sample complexity
Sammy Khalife, Andrea Lodi
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 |
|---|---|---|---|
| train GNN on gap closed instead of B&C tree size (ablation) | GNN cut selector · Set cover | average tree size: 8.27 -> 8.65 | Hurt |
| train GNN on gap closed instead of B&C tree size (ablation) | GNN cut selector · Facility location | average tree size: 128.85 -> 134.61 | Hurt |
| use GNN (tree size) instead of Parallelism heuristic | GNN cut selector · Set cover | average tree size: 8.29 -> 8.27 | No clear effect |
| use GNN (tree size) instead of Parallelism heuristic | GNN cut selector · Facility location | average tree size: 144.09 -> 128.85 | Improved |
| use GNN (gap closed) instead of random selection | GNN cut selector · Facility location | average tree size: 152.46 -> 134.61 | Improved |
Closest papers by meaning
- Learning Cut Generating Functions for Integer Programming (NeurIPS 2024 · similarity 0.91)
- Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut (NeurIPS 2024 · similarity 0.91)
- Generalization Guarantees for Learning Score-Based Branch-and-Cut Policies in Integer Programming (NeurIPS 2025 · similarity 0.88)
- ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems (ICML 2025 · similarity 0.87)
- Learning-Augmented Approximation Algorithms for Maximum Cut and Related Problems (NeurIPS 2024 · similarity 0.85)
- Learn2Aggregate: Supervised Generation of Chvatal-Gomory Cuts Using Graph Neural Networks (AAAI 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.
