Data-driven Prediction of Relevant Scenarios for Robust Combinatorial Optimization
Not on the map. Why?
Abstract (arXiv)
We study iterative methods for (two-stage) robust combinatorial optimization problems with discrete uncertainty. We propose a machine-learning-based heuristic to determine starting scenarios that provide strong lower bounds. To this end, we design dimension-independent features and train a Random Forest Classifier on small-dimensional instances. Experiments show that our method improves the solution process for larger instances than contained in the training set and also provides a feature importance-score which gives insights into the role of scenario properties.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 11 of its 64 references that are in the map. First posted on arXiv 30 Mar 2022.
Builds on
11 of 64 references.
References · 11
- 2019Reinforcement Learning for Integer Programming: Learning to Cutcited by 108
- 2013Data-Driven Robust Optimizationcited by 84
- 2020Parameterizing Branch-and-Bound Search Trees to Learn Branching Policiescited by 62
- 2021Learning to Select Cuts for Efficient Mixed-Integer Programmingcited by 48
- 2022A Survey for Solving Mixed Integer Programming via Machine Learningcited by 44
- 2018Algorithms and Uncertainty Sets for Data-Driven Robust Shortest Path Problemscited by 6
- 2019Oracle-Based Algorithms for Binary Two-Stage Robust Optimizationcited by 3
- 2020Data-Driven Robust Optimization using Unsupervised Deep Learningcited by 3
- 2019Min-Max-Min Robustness for Combinatorial Problems with Discrete Budgeted Uncertaintycited by 2
- 2021Data-Driven Robust Optimization Using Scenario-Induced Uncertainty Setscited by 2
- 2021A Lagrangian Dual Method for Two-Stage Robust Optimization with Binary Uncertaintiescited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.