Beichen Wan, Mo Liu, Paul Grigas, Zuo-Jun Max Shen
The paper proposes a new sequential experimental design approach that improves decision-making by focusing on directional uncertainty, leading to better optimization outcomes than traditional methods.
In many scenarios, we use predictions to make decisions, such as allocating resources or scheduling tasks. However, traditional methods focus on improving prediction accuracy rather than the quality of the decisions made based on those predictions. This research introduces a new approach that prioritizes decision quality by considering the uncertainty in predictions that affect decisions. The method is computationally efficient and has been shown to perform better than older techniques, especially in real-world applications like job allocation using machine learning models.
