Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Prince Zizhuang, Chen, Shuyi, Liang, Jinhao, Fioretto, Ferdinando, Zhu, Shixiang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2502.05468
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912935586037760
author Wang, Prince Zizhuang
Chen, Shuyi
Liang, Jinhao
Fioretto, Ferdinando
Zhu, Shixiang
author_facet Wang, Prince Zizhuang
Chen, Shuyi
Liang, Jinhao
Fioretto, Ferdinando
Zhu, Shixiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_05468
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making
Wang, Prince Zizhuang
Chen, Shuyi
Liang, Jinhao
Fioretto, Ferdinando
Zhu, Shixiang
Machine Learning
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.
title Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making
topic Machine Learning
url https://arxiv.org/abs/2502.05468