Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making

TL;DR

Gen-DFL introduces a generative modeling framework to decision-focused learning, enhancing robustness and performance in high-dimensional, risk-sensitive decision-making problems by adaptively modeling uncertainty.

Contribution

It proposes a novel generative approach for decision-focused learning that improves robustness and handles complex uncertainty in optimization tasks.

Findings

Gen-DFL achieves better worst-case performance bounds.

Empirical results show strong performance on scheduling and logistics problems.

Theoretically, Gen-DFL outperforms traditional DFL in robustness.

Abstract

Decision-focused learning (DFL) integrates predictive models with downstream optimization, directly training machine learning models to minimize decision errors. While DFL has been shown to provide substantial advantages when compared to a counterpart that treats the predictive and prescriptive models separately, it has also been shown to struggle in high-dimensional and risk-sensitive settings, limiting its applicability in real-world settings. To address this limitation, this paper introduces decision-focused generative learning (Gen-DFL), a novel framework that leverages generative models to adaptively model uncertainty and improve decision quality. Instead of relying on fixed uncertainty sets, Gen-DFL learns a structured representation of the optimization parameters and samples from the tail regions of the learned distribution to enhance robustness against worst-case scenarios. This approach mitigates over-conservatism while capturing complex dependencies in the parameter space. The paper shows, theoretically, that Gen-DFL achieves improved worst-case performance bounds compared to traditional DFL. Empirically, it evaluates Gen-DFL on various scheduling and logistics problems, demonstrating its strong performance against existing DFL methods.