# Data-driven Prediction of Relevant Scenarios for Robust Combinatorial Optimization

arXiv: https://arxiv.org/abs/2203.16642 · HTML: https://mlsanity.com/paper/2203.16642/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 64 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 11 of 11)

- [Reinforcement Learning for Integer Programming: Learning to Cut](https://mlsanity.com/paper/1906.04859/) (2019)
- [Data-Driven Robust Optimization](https://mlsanity.com/paper/1401.0212/) (2013)
- [Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies](https://mlsanity.com/paper/2002.05120/) (2020)
- [Learning to Select Cuts for Efficient Mixed-Integer Programming](https://mlsanity.com/paper/2105.13645/) (2021)
- [A Survey for Solving Mixed Integer Programming via Machine Learning](https://mlsanity.com/paper/2203.02878/) (2022)
- [Algorithms and Uncertainty Sets for Data-Driven Robust Shortest Path Problems](https://mlsanity.com/paper/1802.04149/) (2018)
- [Oracle-Based Algorithms for Binary Two-Stage Robust Optimization](https://mlsanity.com/paper/1905.05257/) (2019)
- [Data-Driven Robust Optimization using Unsupervised Deep Learning](https://mlsanity.com/paper/2011.09769/) (2020)
- [Min-Max-Min Robustness for Combinatorial Problems with Discrete Budgeted Uncertainty](https://mlsanity.com/paper/1910.12608/) (2019)
- [Data-Driven Robust Optimization Using Scenario-Induced Uncertainty Sets](https://mlsanity.com/paper/2107.04977/) (2021)
- [A Lagrangian Dual Method for Two-Stage Robust Optimization with Binary Uncertainties](https://mlsanity.com/paper/2112.13138/) (2021)

## Built on by (most cited first, 2 of 2)

- [Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty](https://mlsanity.com/paper/2605.14494/) (2026)
- [Which Directions Matter? Sparse Design for Affine Robust Optimization](https://mlsanity.com/paper/2606.14648/) (2026)

## 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.