Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize

arXiv:2305.16830v2 Announce Type: replace
Abstract: Predict-then-Optimize is a framework for using machine learning to perform decision-making under uncertainty. The central research question it asks is, "How can the structure of a decision-making task be used to tailor ML models for that specific task?" To this end, recent work has proposed learning task-specific loss functions that capture this underlying structure. However, current approaches make restrictive assumptions about the form of these losses and their impact on ML model behavior. These assumptions …

abstract arxiv beyond cs.ai cs.lg decision framework functions loss machine machine learning making ml models question research type uncertainty work