CaVE: A Cone-Aligned Approach for Fast Predict-then-optimize with Binary Linear Programs

arXiv:2312.07718v2 Announce Type: replace
Abstract: The end-to-end predict-then-optimize framework, also known as decision-focused learning, has gained popularity for its ability to integrate optimization into the training procedure of machine learning models that predict the unknown cost (objective function) coefficients of optimization problems from contextual instance information. Naturally, most of the problems of interest in this space can be cast as integer linear programs. In this work, we focus on binary linear programs (BLPs) and propose a new end-to-end training method …

abstract arxiv binary cost cs.lg decision framework function information instance linear machine machine learning machine learning models math.oc optimization the end the unknown training type