Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize
This addresses the challenge of efficient and robust decision-making under uncertainty in machine learning, offering a significant improvement over existing methods.
The paper tackles the problem of restrictive assumptions in learning task-specific loss functions for predict-then-optimize frameworks, which lead to high computational costs and poor performance when violated, and shows that their method achieves state-of-the-art results in four domains, often requiring an order of magnitude fewer samples and outperforming the best existing method by nearly 200% when assumptions are broken.
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 both lead to approaches with high computational cost, and when they are violated in practice, poor performance. In this paper, we propose solutions to these issues, avoiding the aforementioned assumptions and utilizing the ML model's features to increase the sample efficiency of learning loss functions. We empirically show that our method achieves state-of-the-art results in four domains from the literature, often requiring an order of magnitude fewer samples than comparable methods from past work. Moreover, our approach outperforms the best existing method by nearly 200% when the localness assumption is broken.