PAC Prediction Sets Under Label Shift
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: prediction set, label shift, distribution-free uncertainty quantification, probably approximately correct, Clopper-Pearson binomial interval, rejection sampling
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Abstract: Prediction sets capture uncertainty by predicting sets of labels rather than individual labels, enabling downstream decisions to conservatively account for all plausible outcomes. Conformal inference algorithms construct prediction sets guaranteed to contain the true label with high probability. These guarantees fail to hold in the face of distribution shift, which is precisely when reliable uncertainty quantification can be most useful. We propose a novel algorithm for constructing prediction sets with PAC guarantees in the label shift setting, where the probabilities of labels can differ between the source and target distributions. Our algorithm relies on constructing confidence intervals for importance weights by propagating uncertainty through a Gaussian elimination algorithm. We evaluate our approach on four datasets: the CIFAR-10 and ChestX-Ray image datasets, the tabular CDC Heart Dataset, and the AGNews text dataset. Our algorithm satisfies the PAC guarantee while producing smaller prediction set sizes compared to several baselines.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)
Submission Number: 5481
Loading