Log-Driven Semantic Tuning for Mixed Integer Programming Solvers
math.OC, cs.AI, cs.LG
Submitted: 2026-10-31
Updated: 2026-10-31
Comments: 34 pages, 8 figures, 28 tables. Code and data: https://github.com/Zhengzhong-You/LDST
Code: https://github.com/Zhengzhong-You/LDST
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- The SCIP Optimization Suite 9.0
- Automatic MILP Solver Configuration By Learning Problem Similarities
- LLMs for Cold-Start Cutting Plane Separator Configuration
- Large Language Model Agent for Hyper-Parameter Optimization
- GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs
- Small LLMs with Expert Blocks Are Good Enough for Hyperparamter Tuning
- Using Large Language Models for Hyperparameter Optimization
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise