Learning Differentiable Programs with Admissible Neural Heuristics Ameesh Shah
–Neural Information Processing Systems
This relaxed program is differentiable and can be trained end-to-end, and the resulting training loss is an approximately admissible heuristic that can guide the combinatorial search.
Neural Information Processing Systems
Nov-13-2025, 18:24:25 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- Europe
- France (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- North America
- Canada
- British Columbia > Vancouver (0.04)
- Ontario > Essex County
- Windsor (0.04)
- Quebec > Montreal (0.04)
- United States
- Hawaii > Honolulu County
- Honolulu (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Nevada (0.04)
- Oregon > Multnomah County
- Portland (0.04)
- Hawaii > Honolulu County
- Canada
- Asia > Middle East
- Industry:
- Education (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Cognitive Science (0.69)
- Machine Learning
- Neural Networks (0.70)
- Statistical Learning (0.68)
- Natural Language (0.69)
- Representation & Reasoning > Search (1.00)
- Information Technology > Artificial Intelligence