Research map / Learning theory and algorithms / Combinatorial and search optimization
Unsupervised Neural Langevin Sampler for Mixed Integer Linear Programming
Yixin Huang, Shengyu Feng, Yiming 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 |
|---|---|---|---|
| add the second-order correction term to the Erdos loss (ablation) | Ours (Erdos) · CFLP-(100, 100) | objective: 20983.15 -> 19117.49 | Improved |
| add the second-order correction term to the Erdos loss (ablation) | Ours (Erdos) · CFLP-(200, 200) | objective: 39938.12 -> 37998.29 | Improved |
| use correction term instead of an L2-style regularizer (ablation) | Ours (Erdos) · CFLP-(100, 100) | objective: 20217.15 -> 19117.49 | Improved |
| use correction term instead of an L2-style regularizer (ablation) | Ours (Erdos) · CFLP-(200, 200) | objective: 39029.12 -> 37998.29 | Improved |
| add L2-style regularizer E[x'](1-E[x']) without correction term (ablation) | Ours (Erdos) · CFLP-(100, 100) | objective: 20983.15 -> 20217.15 | Improved |
| train with Erdos loss instead of REINFORCE loss (ablation) | Ours · CFLP-(100, 100) | gap to Gurobi (%): 24.13% -> 6.24% | Improved |
| train with Erdos loss instead of Gumbel loss (ablation) | Ours · CFLP-(200, 200) | gap to Gurobi (%): 18.74% -> 11.96% | Improved |
| train with Gumbel loss instead of Erdos loss (ablation) | Ours · IP (Neural Diving 400s) | objective: 13.89 -> 13.82 | Improved |
| train with Gumbel loss instead of Erdos loss (ablation) | Ours · LB (Neural Diving 400s) | objective: 711.92 -> 706.10 | Improved |
| train with Gumbel loss instead of Erdos loss (ablation) | Ours · IP (no downstream solver) | objective: 483.14 -> 481.39 | Improved |
| use unsupervised Ours (Erdos) instead of supervised SL with Neural Diving | Ours (Erdos) · IP (Neural Diving 400s) | objective: 14.62 -> 13.89 | Improved |
| use unsupervised Ours (Erdos) instead of supervised SL on CFLP | Ours (Erdos) · CFLP-(100, 100) | objective: 18731.74 -> 18992.49 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FMIP — FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming (ICLR 2026) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Regularized Langevin Dynamics for Combinatorial Optimization (ICML 2025 · similarity 0.89)
- Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming (ICLR 2025 · similarity 0.89)
- Neural Solver Selection for Combinatorial Optimization (ICML 2025 · similarity 0.87)
- Predicting Lagrangian Multipliers for Mixed Integer Linear Programs (ICML 2024 · similarity 0.86)
- A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization (ICML 2024 · similarity 0.86)
- RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains (NeurIPS 2025 · similarity 0.86)
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.
