Saved in:
Bibliographic Details
Main Authors: Jiménez, Diego, Pagnoncelli, Bernardo K., Yaman, Hande
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.16826
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912228045750272
author Jiménez, Diego
Pagnoncelli, Bernardo K.
Yaman, Hande
author_facet Jiménez, Diego
Pagnoncelli, Bernardo K.
Yaman, Hande
contents The recent interest in contextual optimization problems, where randomness is associated with side information, has led to two primary strategies for formulation and solution. The first, estimate-then-optimize, separates the estimation of the problem's parameters from the optimization process. The second, decision-focused optimization, integrates the optimization problem's structure directly into the prediction procedure. In this work, we propose a pessimistic bilevel approach for solving general decision-focused formulations of combinatorial optimization problems. Our method solves an $\varepsilon$-approximation of the pessimistic bilevel problem using a specialized cut generation algorithm. We benchmark its performance on the 0-1 knapsack problem against estimate-then-optimize and decision-focused methods, including the popular SPO+ approach. Computational experiments highlight the proposed method's advantages, particularly in reducing out-of-sample regret.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16826
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pessimistic bilevel optimization approach for decision-focused learning
Jiménez, Diego
Pagnoncelli, Bernardo K.
Yaman, Hande
Optimization and Control
Discrete Mathematics
90B99
The recent interest in contextual optimization problems, where randomness is associated with side information, has led to two primary strategies for formulation and solution. The first, estimate-then-optimize, separates the estimation of the problem's parameters from the optimization process. The second, decision-focused optimization, integrates the optimization problem's structure directly into the prediction procedure. In this work, we propose a pessimistic bilevel approach for solving general decision-focused formulations of combinatorial optimization problems. Our method solves an $\varepsilon$-approximation of the pessimistic bilevel problem using a specialized cut generation algorithm. We benchmark its performance on the 0-1 knapsack problem against estimate-then-optimize and decision-focused methods, including the popular SPO+ approach. Computational experiments highlight the proposed method's advantages, particularly in reducing out-of-sample regret.
title Pessimistic bilevel optimization approach for decision-focused learning
topic Optimization and Control
Discrete Mathematics
90B99
url https://arxiv.org/abs/2501.16826