Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Spitzer, Victor, Sanson, Francois
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.21883
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918313537306624
author Spitzer, Victor
Sanson, Francois
author_facet Spitzer, Victor
Sanson, Francois
contents Decision-focused learning integrates predictive modeling and combinatorial optimization by training models to directly improve decision quality rather than prediction accuracy alone. Differentiating through combinatorial optimization problems represents a central challenge, and recent approaches tackle this difficulty by introducing perturbation-based approximations. In this work, we focus on estimating the objective function coefficients of a combinatorial optimization problem. Our study demonstrates that fluctuations in perturbation intensity occurring during the learning phase can lead to ineffective training, by establishing a theoretical link to the notion of solution stability in combinatorial optimization. We propose addressing this issue by introducing a regularization of the estimated cost vectors which improves the robustness and reliability of the learning process, as demonstrated by extensive numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21883
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Managing Solution Stability in Decision-Focused Learning with Cost Regularization
Spitzer, Victor
Sanson, Francois
Machine Learning
Decision-focused learning integrates predictive modeling and combinatorial optimization by training models to directly improve decision quality rather than prediction accuracy alone. Differentiating through combinatorial optimization problems represents a central challenge, and recent approaches tackle this difficulty by introducing perturbation-based approximations. In this work, we focus on estimating the objective function coefficients of a combinatorial optimization problem. Our study demonstrates that fluctuations in perturbation intensity occurring during the learning phase can lead to ineffective training, by establishing a theoretical link to the notion of solution stability in combinatorial optimization. We propose addressing this issue by introducing a regularization of the estimated cost vectors which improves the robustness and reliability of the learning process, as demonstrated by extensive numerical experiments.
title Managing Solution Stability in Decision-Focused Learning with Cost Regularization
topic Machine Learning
url https://arxiv.org/abs/2601.21883