Replication Data for: Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities

Decision-focused learning (DFL) is an emerging paradigm that integrates machine learning (ML) and constrained optimization to enhance decision quality by training ML models in an end-to-end system. Our paper presents a comprehensive review of DFL, providing an in-depth analysis of both gradient-based and gradient-free techniques used to combine ML and constrained optimization. It empirically evaluates the strengths and limitations of these techniques and includes an extensive empirical evaluation of eleven methods across seven problems.
This paper has been accepted for publication in The Journal of Artificial Intelligence Research (JAIR). The datasets in this repository have been used to obtain the results reported in the paper. The datasets are provided to ensure reproducibility. To reproduce the result reported in the paper using these datasets refer to \url{https://github.com/PredOpt/predopt-benchmarks}.