Research map / Learning theory and algorithms / Combinatorial and search optimization
Neur2SP: Neural Two-Stage Stochastic Programming
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 NN-E to predict the expected second-stage value for a scenario set instead of NN-P's per-scenario predictions (ablation) | Neur2SP · CFLP, SSLP, INVP, and PP | solving time: NN-E solving time ranges from 0.11s to 1.66s; NN-P takes up to 10,853.59 seconds | Helped |
| Use NN-E instead of NN-P (ablation) | Neur2SP · PP | objective difference (%): 40.85 -> 0.67 | Helped |
| Use NN-E instead of the extensive form | Neur2SP · SSLP_10_50_2000 | solving time: 10,800.17 -> 0.14 | Helped |
| Use NN-E instead of the extensive form | Neur2SP · CFLP_50_50_1000 | objective difference (%): EF-NN-E: -16.62 | Helped |
| Use NN-P instead of NN-E (ablation) | Neur2SP · Pooling Problem | objective difference (%): NN-P around 40%; NN-E less than 5% in most cases | Hurt |
Closest papers by meaning
- HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming (ICML 2024 · similarity 0.89)
- Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty (NeurIPS 2026 · similarity 0.88)
- Learning Generalized Linear Programming Value Functions (NeurIPS 2024 · similarity 0.85)
- BayeSQP: Bayesian Optimization through Sequential Quadratic Programming (NeurIPS 2025 · similarity 0.85)
- Neural Combinatorial Optimization for Stochastic Flexible Job Shop Scheduling Problems (AAAI 2025 · similarity 0.84)
- Multi-Stage Predict+Optimize for (Mixed Integer) Linear Programs (NeurIPS 2024 · 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.