Research map / Learning theory and algorithms / Combinatorial and search optimization
Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model
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 HEM instead of SBP | MILP cut selection · Set Covering | Time (s): 1.91 (0.36) -> 1.85 (0.31) | Helped |
| Use HEM instead of SBP | MILP cut selection · Maximum Independent Set | Time (s): 2.43 (5.55) -> 1.76 (3.69) | Helped |
| Use HEM instead of SBP | MILP cut selection · Multiple Knapsack | Time (s): 7.74 (12.36) -> 6.13 (9.61) | Helped |
| Use HEM instead of Default | MILP cut selection · MIK | PD integral: 844.40 (924.30) -> 785.04 (790.38) | Helped |
| Use HEM instead of SBP | MILP cut selection · CORLAT | PD integral: 2023.87 (5085.96) -> 1079.99 (2653.14) | Helped |
| Use HEM instead of Default | MILP cut selection · Load Balancing | PD integral: 9589.19 (1012.95) -> 9496.42 (1018.35) | Helped |
| Use HEM instead of Random | MILP cut selection · Anonymous | PD integral: 16850.89 (10227.87) -> 16077.15 (9108.21) | Helped |
| Use HEM instead of SBP | MILP cut selection · MIPLIB mixed neos | PD integral: 13531.00 (12898.22) -> 8678.76 (12337.00) | Helped |
| Use HEM instead of SBP | MILP cut selection · MIPLIB mixed supportcase | PD integral: 7408.65 (7903.47) -> 6874.80 (6729.97) | Helped |
| Use HEM instead of NV | MILP cut selection · Production Planning | Time (s): 259.48 (227.81) -> 241.77 (229.97) | Helped |
| Add the higher-level model that learns the cut count (ablation) | HEM · Maximum Independent Set | PD integral: 16.70 (28.15) -> 16.01 (26.21) | Helped |
| Add the higher-level model that learns the cut count (ablation) | HEM · CORLAT | PD integral: 1939.08 (5484.83) -> 1079.99 (2653.14) | Helped |
Closest papers by meaning
- Learning to Stop Cut Generation for Efficient Mixed-Integer Linear Programming (AAAI 2024 · similarity 0.92)
- Learning to Remove Cuts in Integer Linear Programming (ICML 2024 · similarity 0.91)
- Generalization Guarantees for Learning Score-Based Branch-and-Cut Policies in Integer Programming (NeurIPS 2025 · similarity 0.89)
- Fast and Interpretable Mixed-Integer Linear Program Solving by Learning Model Reduction (AAAI 2025 · similarity 0.88)
- Learning Cut Generating Functions for Integer Programming (NeurIPS 2024 · similarity 0.88)
- Accelerating Cutting-Plane Algorithms via Reinforcement Learning Surrogates (AAAI 2024 · similarity 0.87)
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.