The paper introduces the Label-Shift-Adjusted Bayesian Score (LSA score), a nonconformity measure for conformal prediction that corrects Bayesian scores under label shift by applying an importance-weighted transformation of the source predictive distribution. Unlike residual-based scores that produce uniform-width intervals, the LSA score yields shorter, adaptive intervals while maintaining comparable coverage in the target domain. Experiments on molecular property prediction demonstrate that the LSA score outperforms both residual-based and source-based Bayesian scores, though all methods experience some coverage loss under stronger shifts due to density-ratio estimation challenges.
By Hyeonsu Lee, Juyeon Kim, Erkhembayar Jadamba, Seungjin Choi, Hyunjin Shin
arXiv:2609.30886v1 Announce Type: new
Abstract: Conformal prediction can lose coverage when the data distribution changes after deployment. We study adaptation using labeled source data and unlabeled...
By Seungjin Choi
arXiv:2606. 11865v1 Announce Type: cross Abstract: Conformal Bayes combines Bayesian posterior predictives with conformal calibration to produce prediction sets that are both statistically valid and geometrically efficient.
By Seungjin Choi
Conformal Bayes combines Bayesian posterior predictives with conformal calibration to produce prediction sets that are both statistically valid and geometrically efficient. We study conformal Bayes under label shift from a unified perspective, identifying two complementary approaches that restore nominal target-domain coverage through importance-weighted conformal calibration but operate through independent mechanisms.
arXiv:2606. 15217v1 Announce Type: cross Abstract: Offline model-based optimization (MBO) proposes candidates by optimizing a surrogate trained on a fixed historical dataset.
By Seungjin Choi
arXiv:2607. 04236v1 Announce Type: cross Abstract: Bayes-assisted conformal prediction combines the strengths of Bayesian modelling with exact, distribution-free frequentist coverage guarantees.
By Kianoosh Ashouritaklimi, Stefano Cortinovis, Fran\c{c}ois Caron
arXiv:2604. 06464v2 Announce Type: replace Abstract: Conformal prediction provides distribution-free prediction intervals with finite-sample coverage guarantees, and recent work by Snell \& Griffiths reframes it as Bayesian Quadrature (BQ-CP), yielding powerful data-conditional guarantees via Dirichlet posteriors over thresholds.
By Xiayin Lou, Peng Luo
arXiv:2607. 22985v1 Announce Type: cross Abstract: Conformalized selection has been widely applied to select high-quality candidates from large datasets with rigorous uncertainty quantification, such as reliable labeling, drug discovery, and the alignment of large language models.
By Chengyao Yu, Hongxin Wei, Bingyi Jing
arXiv:2606. 03600v1 Announce Type: cross Abstract: Standard conformal prediction (CP) procedures are typically formulated in terms of p-values, but reliance on p-values alone limits flexibility, for example, when combining dependent evidence across models or data splits.
By Nabil Alami, Jad Zakharia, Souhaib Ben Taieb
arXiv:2607. 16675v1 Announce Type: cross Abstract: A point prediction that is well calibrated on average can still be systematically biased conditional on its own value, undermining its use in downstream decision-making.
By Daniel Bensimon, Sean Xiang Yu, Eric D. Kolaczyk, Archer Y. Yang
arXiv:2608. 06206v1 Announce Type: cross Abstract: Conformal prediction endows arbitrary black-box predictors with finite-sample, distribution-free marginal coverage, yet marginal validity can hide severe covariate-specific miscalibration, while exact distribution-free conditional coverage is finite-sample unattainable.
By Anton Conrad, Rustam Isaev, Denis Belomestny, Eric Moulines, Sergey Samsonov
arXiv:2508.10336v3 Announce Type: replace-cross
Abstract: In a supervised online setting, quantifying uncertainty has been proposed in the seminal work of Gibbs and Cand\`es (2021). For any given poi...
By Pierre Humbert, Ulysse Gazin, Ruth Heller, Etienne Roquain