Robust Losses for Decision-Focused Learning

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

33 Downloads (Pure)

Abstract

Optimization models used to make discrete decisions often contain uncertain parameters that are context-dependent and estimated through prediction. To account for the quality of the decision made based on the prediction, decision-focused learning (end-to-end predict-then-optimize) aims at training the predictive model to minimize regret, i.e., the loss incurred by making a suboptimal decision. Despite the challenge of the gradient of this loss w.r.t. the predictive model parameters being zero almost everywhere for optimization problems with a linear objective, effective gradient-based learning approaches have been proposed to minimize the expected loss, using the empirical loss as a surrogate. However, empirical regret can be an ineffective surrogate because empirical optimal decisions can vary substantially from expected optimal decisions. To understand the impact of this deficiency, we evaluate the effect of aleatoric and epistemic uncertainty on the accuracy of empirical regret as a surrogate. Next, we propose three novel loss functions that approximate expected regret more robustly. Experimental results show that training two state-of-the-art decision-focused learning approaches using robust regret losses improves test–sample empirical regret in general while keeping computational time equivalent relative to the number of training epochs.
Original languageEnglish
Title of host publicationProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
EditorsKate Larson
Pages4868-4875
Number of pages8
ISBN (Electronic)978-1-956792-04-1
DOIs
Publication statusPublished - 2024
Event33rd International Joint Conference on Artificial Intelligence - International Convention Center Jeju (ICC Jeju), Jeju Island, Korea, Republic of
Duration: 3 Aug 20249 Aug 2024
Conference number: 33
https://ijcai24.org/

Conference

Conference33rd International Joint Conference on Artificial Intelligence
Abbreviated titleIJCAI 2024
Country/TerritoryKorea, Republic of
CityJeju Island
Period3/08/249/08/24
Internet address

Fingerprint

Dive into the research topics of 'Robust Losses for Decision-Focused Learning'. Together they form a unique fingerprint.

Cite this