Skip to content
arXiv stat.ML · Papers

Conformal Bayes under Label Shift: Post-Hoc Calibration vs. In-Training Adaptation

arXiv:2606.11865v2 Announce Type: replace Abstract: 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 compleme