Research map / Learning theory and algorithms / Combinatorial and search optimization
Data-Driven Approximations to NP-Hard Problems
Anton Milan, S. Rezatofighi, Ravi Garg, Anthony Dick, Ian Reid
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 objective-based gradient replacement instead of loss-only training (ablation) | LSTM · Synthetic tracking | OSPA-T: 0.42 -> 0.37 | Improved |
| train with objective-based gradient replacement instead of loss-only training (ablation) | LSTM · Synthetic tracking | ID switches: 0.70 -> 0.60 | Improved |
| train with objective-based gradient replacement instead of loss-only training (ablation) | LSTM · Feature point matching (motorbikes) | accuracy: 0.68 -> 0.76 | Improved |
| train with objective-based gradient replacement instead of loss-only training (ablation) | LSTM · Feature point matching (motorbikes) | objective: 9.54 -> 10.52 | Improved |
| add objective-based gradient replacement to Pointer-Net training (ablation) | Pointer-Net · TSP 20 nodes, Qatar map | tour length: 3.80 -> 3.45 | Improved |
| train LSTM on approximate JPDA10 labels only | LSTM · Synthetic tracking | OSPA-T: 0.43 -> 0.42 | Improved |
| use LSTM (obj.) instead of exact JPDA | LSTM · Synthetic tracking | ID switches: 0.40 -> 0.60 | Hurt |
Closest papers by meaning
- Neural Solver Selection for Combinatorial Optimization (ICML 2025 · similarity 0.86)
- NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks (NeurIPS 2024 · similarity 0.86)
- Are Graph Neural Networks Optimal Approximation Algorithms? (NeurIPS 2024 · similarity 0.85)
- Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs (ICML 2025 · similarity 0.85)
- Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning (NeurIPS 2025 · similarity 0.85)
- Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problem (ICML 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.
