Robust Decision-Focused Learning via Worst-Case Regret Minimization

Shoki Yamao, Ken Kobayashi, Ryo Matsui, Shota Nagai, Naoki Nishimura, Kazuhide Nakata
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:7701-7736, 2026.

Abstract

In optimization-based decision-making, when the objective coefficient vector is unknown, a common approach is to predict it from covariates using a machine learning model and solve the downstream optimization problem. However, improving predictive accuracy does not necessarily lead to better decisions. This has motivated Decision-Focused Learning (DFL), which trains predictive models to minimize decision loss measured by regret. Despite recent progress, existing DFL methods do not sufficiently address two sources of uncertainty: (i) observation errors in the measured coefficients, and (ii) distribution shift in the coefficient vector at deployment due to environmental changes. These uncertainties can degrade solution quality. In this paper, we propose two robust regret losses to address these uncertainties. For uncertainty (i), we introduce an uncertainty set around the observed coefficient vector that captures measurement errors and define the loss as the worst-case regret over this set. For uncertainty (ii), we construct a {Wasserstein} ambiguity set around the conditional empirical distribution and define the loss using the worst-case distribution within the set. We enable efficient training via Danskin-based subgradients. Experiments demonstrate that our method reduces regret and yields more stable solutions than existing robust DFL approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-yamao26a, title = {Robust Decision-Focused Learning via Worst-Case Regret Minimization}, author = {Yamao, Shoki and Kobayashi, Ken and Matsui, Ryo and Nagai, Shota and Nishimura, Naoki and Nakata, Kazuhide}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {7701--7736}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/yamao26a/yamao26a.pdf}, url = {https://proceedings.mlr.press/v337/yamao26a.html}, abstract = {In optimization-based decision-making, when the objective coefficient vector is unknown, a common approach is to predict it from covariates using a machine learning model and solve the downstream optimization problem. However, improving predictive accuracy does not necessarily lead to better decisions. This has motivated Decision-Focused Learning (DFL), which trains predictive models to minimize decision loss measured by regret. Despite recent progress, existing DFL methods do not sufficiently address two sources of uncertainty: (i) observation errors in the measured coefficients, and (ii) distribution shift in the coefficient vector at deployment due to environmental changes. These uncertainties can degrade solution quality. In this paper, we propose two robust regret losses to address these uncertainties. For uncertainty (i), we introduce an uncertainty set around the observed coefficient vector that captures measurement errors and define the loss as the worst-case regret over this set. For uncertainty (ii), we construct a {Wasserstein} ambiguity set around the conditional empirical distribution and define the loss using the worst-case distribution within the set. We enable efficient training via Danskin-based subgradients. Experiments demonstrate that our method reduces regret and yields more stable solutions than existing robust DFL approaches.} }
Endnote
%0 Conference Paper %T Robust Decision-Focused Learning via Worst-Case Regret Minimization %A Shoki Yamao %A Ken Kobayashi %A Ryo Matsui %A Shota Nagai %A Naoki Nishimura %A Kazuhide Nakata %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-yamao26a %I PMLR %P 7701--7736 %U https://proceedings.mlr.press/v337/yamao26a.html %V 337 %X In optimization-based decision-making, when the objective coefficient vector is unknown, a common approach is to predict it from covariates using a machine learning model and solve the downstream optimization problem. However, improving predictive accuracy does not necessarily lead to better decisions. This has motivated Decision-Focused Learning (DFL), which trains predictive models to minimize decision loss measured by regret. Despite recent progress, existing DFL methods do not sufficiently address two sources of uncertainty: (i) observation errors in the measured coefficients, and (ii) distribution shift in the coefficient vector at deployment due to environmental changes. These uncertainties can degrade solution quality. In this paper, we propose two robust regret losses to address these uncertainties. For uncertainty (i), we introduce an uncertainty set around the observed coefficient vector that captures measurement errors and define the loss as the worst-case regret over this set. For uncertainty (ii), we construct a {Wasserstein} ambiguity set around the conditional empirical distribution and define the loss using the worst-case distribution within the set. We enable efficient training via Danskin-based subgradients. Experiments demonstrate that our method reduces regret and yields more stable solutions than existing robust DFL approaches.
APA
Yamao, S., Kobayashi, K., Matsui, R., Nagai, S., Nishimura, N. & Nakata, K.. (2026). Robust Decision-Focused Learning via Worst-Case Regret Minimization. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:7701-7736 Available from https://proceedings.mlr.press/v337/yamao26a.html.

Related Material