Research map / Learning theory and algorithms / Combinatorial and search optimization
ASP: Learn a Universal Neural Solver!
Chenguang Wang, Zhouliang Yu, Stephen McAleer, Tianshu Yu, Yaodong Yang
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 with ASP (distributional exploration + persistent scale adaption) | AM · TSP (generated) | Avg. gap: 41.67% -> 3.79% | Improved |
| train with ASP | POMO · TSP (generated) | Avg. gap: 1.09% -> 0.78% | Improved |
| train with ASP | AM · CVRP (generated) | Avg. gap: 11.72% -> 9.49% | Improved |
| train with ASP | POMO · CVRP (generated) | Avg. gap: 1.53% -> 1.47% | Improved |
| train with ASP | AM · PCTSP | Avg. gap: 16.69% -> 11.32% | Improved |
| train with ASP | AM · SPCTSP | Avg. gap: 17.45% -> 8.86% | Improved |
| train with ASP | AM · TSP n=20 | optimality gap: 5.95% -> 1.81% | Improved |
| train with ASP | POMO · TSP n=20 | optimality gap: 0.01% -> 0.09% | Hurt |
| train with ASP | AM · PCTSP n=20 | optimality gap: 2.88% -> 12.05% | Hurt |
| train with ASP | AM · TSPLib | Avg. gap: 10.69 -> 5.62 | Improved |
| train with ASP | POMO · CVRPLib | Avg. gap: 6.10 -> 3.32 | Improved |
| train with ASP instead of uniform mixed-scale training (ablation) | AM · TSP and CVRP | optimality gap | Improved |
Closest papers by meaning
- Neural Solver Selection for Combinatorial Optimization (ICML 2025 · similarity 0.89)
- UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP (ICLR 2025 · similarity 0.89)
- SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver (NeurIPS 2026 · similarity 0.86)
- Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization (NeurIPS 2024 · similarity 0.85)
- Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP (NeurIPS 2025 · similarity 0.85)
- Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning (NeurIPS 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.
