Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction

Lars Van Der Laan, Ahmed Alaa
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60748-60763, 2025.

Abstract

Ensuring model calibration is critical for reliable prediction, yet popular distribution-free methods such as histogram binning and isotonic regression offer only asymptotic guarantees. We introduce a unified framework for Venn and Venn-Abers calibration that extends Vovk’s approach beyond binary classification to a broad class of prediction tasks defined by generic loss functions. Our method transforms any perfectly in-sample calibrated predictor into a set-valued predictor that, in finite samples, outputs at least one marginally calibrated point prediction. These set predictions shrink asymptotically and converge to a conditionally calibrated prediction, capturing epistemic uncertainty. We further propose Venn multicalibration, a new approach for achieving finite-sample calibration across subpopulations. For quantile loss, our framework recovers group-conditional and multicalibrated conformal prediction as special cases and yields novel prediction intervals with quantile-conditional coverage.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-van-der-laan25a, title = {Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction}, author = {Van Der Laan, Lars and Alaa, Ahmed}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {60748--60763}, 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/van-der-laan25a/van-der-laan25a.pdf}, url = {https://proceedings.mlr.press/v267/van-der-laan25a.html}, abstract = {Ensuring model calibration is critical for reliable prediction, yet popular distribution-free methods such as histogram binning and isotonic regression offer only asymptotic guarantees. We introduce a unified framework for Venn and Venn-Abers calibration that extends Vovk’s approach beyond binary classification to a broad class of prediction tasks defined by generic loss functions. Our method transforms any perfectly in-sample calibrated predictor into a set-valued predictor that, in finite samples, outputs at least one marginally calibrated point prediction. These set predictions shrink asymptotically and converge to a conditionally calibrated prediction, capturing epistemic uncertainty. We further propose Venn multicalibration, a new approach for achieving finite-sample calibration across subpopulations. For quantile loss, our framework recovers group-conditional and multicalibrated conformal prediction as special cases and yields novel prediction intervals with quantile-conditional coverage.} }
Endnote
%0 Conference Paper %T Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction %A Lars Van Der Laan %A Ahmed Alaa %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-van-der-laan25a %I PMLR %P 60748--60763 %U https://proceedings.mlr.press/v267/van-der-laan25a.html %V 267 %X Ensuring model calibration is critical for reliable prediction, yet popular distribution-free methods such as histogram binning and isotonic regression offer only asymptotic guarantees. We introduce a unified framework for Venn and Venn-Abers calibration that extends Vovk’s approach beyond binary classification to a broad class of prediction tasks defined by generic loss functions. Our method transforms any perfectly in-sample calibrated predictor into a set-valued predictor that, in finite samples, outputs at least one marginally calibrated point prediction. These set predictions shrink asymptotically and converge to a conditionally calibrated prediction, capturing epistemic uncertainty. We further propose Venn multicalibration, a new approach for achieving finite-sample calibration across subpopulations. For quantile loss, our framework recovers group-conditional and multicalibrated conformal prediction as special cases and yields novel prediction intervals with quantile-conditional coverage.
APA
Van Der Laan, L. & Alaa, A.. (2025). Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:60748-60763 Available from https://proceedings.mlr.press/v267/van-der-laan25a.html.

Related Material