Risk-Controlling Prediction with Distributionally Robust Optimization
Abstract
Conformal prediction is a popular paradigm to quantify the uncertainty of a model's output on a new batch of data. Quite differently, distributionally robust optimization aims at training a model that is robust to uncertainties in the distribution of the training data. In this paper, we examine the links between the two approaches. In particular, we show that we can learn conformal prediction intervals by distributionally robust optimization on a well chosen objective. This further entails to train a model and build conformal prediction intervals all at once, using the same data.
Cite
Text
Iutzeler and Mazoyer. "Risk-Controlling Prediction with Distributionally Robust Optimization." Transactions on Machine Learning Research, 2025.Markdown
[Iutzeler and Mazoyer. "Risk-Controlling Prediction with Distributionally Robust Optimization." Transactions on Machine Learning Research, 2025.](https://mlanthology.org/tmlr/2025/iutzeler2025tmlr-riskcontrolling/)BibTeX
@article{iutzeler2025tmlr-riskcontrolling,
title = {{Risk-Controlling Prediction with Distributionally Robust Optimization}},
author = {Iutzeler, Franck and Mazoyer, Adrien},
journal = {Transactions on Machine Learning Research},
year = {2025},
url = {https://mlanthology.org/tmlr/2025/iutzeler2025tmlr-riskcontrolling/}
}