Coverage Guarantees for Pseudo-Calibrated Conformal Prediction under Distribution Shift
Not on the map. Why?
Abstract (arXiv)
Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data distribution shifts. We analyze the use of pseudo-calibration as a tool to counter this performance loss under a bounded label-conditional covariate shift model. Using tools from domain adaptation, we derive a lower bound on target coverage in terms of the source-domain loss of the classifier and a Wasserstein measure of the shift. Using this result, we provide a method to design pseudo-calibrated sets that inflate the conformal threshold by a slack parameter to keep target coverage above a prescribed level. Finally, we propose a source-tuned pseudo-calibration algorithm that interpolates between hard pseudo-labels and randomized labels as a function of classifier uncertainty. Numerical experiments show that our bounds qualitatively track pseudo-calibration behavior and that the source-tuned scheme mitigates coverage degradation under distribution shift while maintaining nontrivial prediction set sizes.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 26 references that are in the map. First posted on arXiv 16 Feb 2026.
Builds on
22 of 26 references.
References · 22
- 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
- 2019Conformal Prediction Under Covariate Shiftcited by 511
- 2022Conformal prediction beyond exchangeabilitycited by 348
- 2022Conformal Risk Controlcited by 290
- 2020Conformal Inference of Counterfactuals and Individual Treatment Effectscited by 150
- 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
- 2021Distribution-free uncertainty quantification for classification under label shiftcited by 99
- 2024Theoretical Foundations of Conformal Predictioncited by 96
- 2020Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptationcited by 43
- 2021PAC Prediction Sets Under Covariate Shiftcited by 42
- 2022Doubly Robust Calibration of Prediction Sets under Covariate Shiftcited by 40
- 2023Gradual Domain Adaptation: Theory and Algorithmscited by 18
10 more
- 2025Wasserstein-regularized Conformal Prediction under General Distribution Shiftcited by 14
- 2025Conformal Prediction under Levy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbationscited by 11
- 2025Probably Approximately Correct Labelscited by 7
- 2024Adapting Prediction Sets to Distribution Shifts Without Labelscited by 6
- 2025Mirror Online Conformal Prediction with Intermittent Feedbackcited by 6
- 2025WQLCP: Weighted Adaptive Conformal Prediction for Robust Uncertainty Quantification Under Distribution Shiftscited by 5
- 2025Non-exchangeable Conformal Prediction with Optimal Transport: Tackling Distribution Shifts with Unlabeled Datacited by 4
- 2024Learning minimal volume uncertainty ellipsoidscited by 2
- 2025Multiply Robust Conformal Risk Control with Coarsened Datacited by 2
- 2025Optimizing In-Context Learning for Efficient Full Conformal Predictioncited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.