Aligning Learning and Endogenous Decision-Making
This academic paper introduces a novel end-to-end framework for solving contextual stochastic optimization problems where decisions directly influence outcomes, unlike traditional approaches. The authors propose a robust optimization variant that accounts for machine learning model uncertainty by constructing uncertainty sets to optimize actions against worst-case predictions, proving it can achieve near-optimal decisions with high probability. Additionally, they present a new class of two-stage stochastic optimization problems focused on information gathering before a second-stage decision. The framework's effectiveness is demonstrated through computational experiments on pricing, inventory assortment, and electricity scheduling, showing improved performance over existing methods. The paper also provides a detailed theoretical analysis of its proposed methods, including generalization bounds.