Online conformal prediction with decaying step sizes

Anastasios Nikolas Angelopoulos, Rina Barber, Stephen Bates
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1616-1630, 2024.

Abstract

We introduce a method for online conformal prediction with decaying step sizes. Like previous methods, ours possesses a retrospective guarantee of coverage for arbitrary sequences. However, unlike previous methods, we can simultaneously estimate a population quantile when it exists. Our theory and experiments indicate substantially improved practical properties: in particular, when the distribution is stable, the coverage is close to the desired level for every time point, not just on average over the observed sequence.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-angelopoulos24a, title = {Online conformal prediction with decaying step sizes}, author = {Angelopoulos, Anastasios Nikolas and Barber, Rina and Bates, Stephen}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {1616--1630}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/angelopoulos24a/angelopoulos24a.pdf}, url = {https://proceedings.mlr.press/v235/angelopoulos24a.html}, abstract = {We introduce a method for online conformal prediction with decaying step sizes. Like previous methods, ours possesses a retrospective guarantee of coverage for arbitrary sequences. However, unlike previous methods, we can simultaneously estimate a population quantile when it exists. Our theory and experiments indicate substantially improved practical properties: in particular, when the distribution is stable, the coverage is close to the desired level for every time point, not just on average over the observed sequence.} }
Endnote
%0 Conference Paper %T Online conformal prediction with decaying step sizes %A Anastasios Nikolas Angelopoulos %A Rina Barber %A Stephen Bates %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-angelopoulos24a %I PMLR %P 1616--1630 %U https://proceedings.mlr.press/v235/angelopoulos24a.html %V 235 %X We introduce a method for online conformal prediction with decaying step sizes. Like previous methods, ours possesses a retrospective guarantee of coverage for arbitrary sequences. However, unlike previous methods, we can simultaneously estimate a population quantile when it exists. Our theory and experiments indicate substantially improved practical properties: in particular, when the distribution is stable, the coverage is close to the desired level for every time point, not just on average over the observed sequence.
APA
Angelopoulos, A.N., Barber, R. & Bates, S.. (2024). Online conformal prediction with decaying step sizes. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:1616-1630 Available from https://proceedings.mlr.press/v235/angelopoulos24a.html.

Related Material