Research map / Learning theory and algorithms / Optimal transport
Optimal Transport–Guided Stochastic Control for Graph Combinatorial Optimization
Yang Huang, Yifan Zhang, Jian Cheng
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 |
|---|---|---|---|
| add neural guidance instead of Nesterov optimization for the Laplace subproblem (ablation) | OT-guided stochastic control · MIS RB-[200–300] | best Laplace energy: -15.53 -> -19.13 | Improved |
| increase number of particles K (16 to 128) (ablation) | OT-guided stochastic control · MIS RB-[200–300] | average MIS size | Improved |
| increase number of optimization steps T (20 to 500) (ablation) | OT-guided stochastic control · MIS RB-[200–300] | average MIS size | Improved |
| increase budget from 100x20 to 500x64 | OT-guided stochastic control · MIS RB-[200–300] | average independent set size: 19.652 -> 20.12 | Improved |
| increase budget from 100x20 to 500x64 | OT-guided stochastic control · MaxCl RB-[800–1200] | clique size: 37.73 -> 40.52 | Improved |
| increase budget from 100x20 to 500x64 | OT-guided stochastic control · MIS RB-[200–300] | runtime per instance (s): 0.562 -> 6.381 | Hurt |
Closest papers by meaning
- Bayesian Optimization of Functions over Node Subsets in Graphs (NeurIPS 2024 · similarity 0.87)
- Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference (NeurIPS 2025 · similarity 0.86)
- AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs (NeurIPS 2026 · similarity 0.86)
- Efficient Combinatorial Optimization via Heat Diffusion (NeurIPS 2024 · similarity 0.86)
- Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning (NeurIPS 2026 · similarity 0.85)
- Are Graph Neural Networks Optimal Approximation Algorithms? (NeurIPS 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.
