Strategic Conformal Prediction
Abstract
When a machine learning model is deployed, its predictions can alter its environment, as better informed agents strategize to suit their own interests. With such alterations in mind, existing approaches to uncertainty quantification break. In this work we propose a new framework, Strategic Conformal Prediction, which is capable of robust uncertainty quantification in such a setting. Strategic Conformal Prediction is backed by a series of theoretical guarantees spanning marginal coverage, training-conditional coverage, tightness and robustness to misspecification that hold in a distribution-free manner. Experimental analysis further validates our method, showing its remarkable effectiveness in face of arbitrary strategic alterations, whereas other methods break.
Cite
Text
Csillag et al. "Strategic Conformal Prediction." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.Markdown
[Csillag et al. "Strategic Conformal Prediction." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.](https://mlanthology.org/aistats/2025/csillag2025aistats-strategic/)BibTeX
@inproceedings{csillag2025aistats-strategic,
title = {{Strategic Conformal Prediction}},
author = {Csillag, Daniel and Struchiner, Claudio Jose and Goedert, Guilherme Tegoni},
booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
year = {2025},
pages = {5122-5130},
volume = {258},
url = {https://mlanthology.org/aistats/2025/csillag2025aistats-strategic/}
}