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

TL;DR

This paper introduces a novel approach for designing task-specific loss functions in predict-then-optimize frameworks, improving sample efficiency and robustness beyond existing methods, especially when traditional assumptions are violated.

Contribution

It proposes a new method that avoids restrictive assumptions, uses model features to enhance learning efficiency, and achieves state-of-the-art results across multiple domains.

Findings

Achieves state-of-the-art results in four literature domains.

Requires up to ten times fewer samples than previous methods.

Outperforms existing methods by nearly 200% when localness assumptions are broken.

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 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.