Online Differentially Private Conformal Prediction for Uncertainty Quantification

Qiangqiang Zhang, Ting Li, Xinwei Feng, Xiaodong Yan, Jinhan Xie
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75329-75368, 2025.

Abstract

Traditional conformal prediction faces significant challenges with the rise of streaming data and increasing concerns over privacy. In this paper, we introduce a novel online differentially private conformal prediction framework, designed to construct dynamic, model-free private prediction sets. Unlike existing approaches that either disregard privacy or require full access to the entire dataset, our proposed method ensures individual privacy with a one-pass algorithm, ideal for real-time, privacy-preserving decision-making. Theoretically, we establish guarantees for long-run coverage at the nominal confidence level. Moreover, we extend our method to conformal quantile regression, which is fully adaptive to heteroscedasticity. We validate the effectiveness and applicability of the proposed method through comprehensive simulations and real-world studies on the ELEC2 and PAMAP2 datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zhang25ap, title = {Online Differentially Private Conformal Prediction for Uncertainty Quantification}, author = {Zhang, Qiangqiang and Li, Ting and Feng, Xinwei and Yan, Xiaodong and Xie, Jinhan}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {75329--75368}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zhang25ap/zhang25ap.pdf}, url = {https://proceedings.mlr.press/v267/zhang25ap.html}, abstract = {Traditional conformal prediction faces significant challenges with the rise of streaming data and increasing concerns over privacy. In this paper, we introduce a novel online differentially private conformal prediction framework, designed to construct dynamic, model-free private prediction sets. Unlike existing approaches that either disregard privacy or require full access to the entire dataset, our proposed method ensures individual privacy with a one-pass algorithm, ideal for real-time, privacy-preserving decision-making. Theoretically, we establish guarantees for long-run coverage at the nominal confidence level. Moreover, we extend our method to conformal quantile regression, which is fully adaptive to heteroscedasticity. We validate the effectiveness and applicability of the proposed method through comprehensive simulations and real-world studies on the ELEC2 and PAMAP2 datasets.} }
Endnote
%0 Conference Paper %T Online Differentially Private Conformal Prediction for Uncertainty Quantification %A Qiangqiang Zhang %A Ting Li %A Xinwei Feng %A Xiaodong Yan %A Jinhan Xie %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zhang25ap %I PMLR %P 75329--75368 %U https://proceedings.mlr.press/v267/zhang25ap.html %V 267 %X Traditional conformal prediction faces significant challenges with the rise of streaming data and increasing concerns over privacy. In this paper, we introduce a novel online differentially private conformal prediction framework, designed to construct dynamic, model-free private prediction sets. Unlike existing approaches that either disregard privacy or require full access to the entire dataset, our proposed method ensures individual privacy with a one-pass algorithm, ideal for real-time, privacy-preserving decision-making. Theoretically, we establish guarantees for long-run coverage at the nominal confidence level. Moreover, we extend our method to conformal quantile regression, which is fully adaptive to heteroscedasticity. We validate the effectiveness and applicability of the proposed method through comprehensive simulations and real-world studies on the ELEC2 and PAMAP2 datasets.
APA
Zhang, Q., Li, T., Feng, X., Yan, X. & Xie, J.. (2025). Online Differentially Private Conformal Prediction for Uncertainty Quantification. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:75329-75368 Available from https://proceedings.mlr.press/v267/zhang25ap.html.

Related Material