mlsanityData to 14 Oct 2026

Training-Conditional Coverage Bounds under Covariate Shift

arXiv 2405.16594 ↗First posted 26 May 2024stat.ML cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Conformal prediction methodology has recently been extended to the covariate shift setting, where the distribution of covariates differs between training and test data. While existing results ensure that the prediction sets from these methods achieve marginal coverage above a nominal level, their coverage rate conditional on the training dataset (referred to as training-conditional coverage) remains unexplored. In this paper, we address this gap by deriving upper bounds on the tail of the training-conditional coverage distribution, offering probably approximately correct (PAC) guarantees for these methods. Our results characterize the reliability of the prediction sets in terms of the severity of distributional changes and the size of the training dataset.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 17 of its 52 references that are in the map. First posted on arXiv 26 May 2024.

Builds on

17 of 52 references.

References · 17

  1. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  2. 2019Conformal Prediction Under Covariate Shiftcited by 519
  3. 2019Predictive inference with the jackknife+cited by 211
  4. 2020Predicting What You Already Know Helps: Provable Self-Supervised Learningcited by 152
  5. 2023Conformal Prediction With Conditional Guaranteescited by 152
  6. 2020Conformal Inference of Counterfactuals and Individual Treatment Effectscited by 151
  7. 2021Localized Conformal Prediction: A Generalized Inference Framework for Conformal Predictioncited by 114
  8. 2021Distribution-free uncertainty quantification for classification under label shiftcited by 101
  9. 2022Batch Multivalid Conformal Predictioncited by 67
  10. 2022Optimally tackling covariate shift in RKHS-based nonparametric regressioncited by 54
  11. 2020Domain adaptation under structural causal modelscited by 28
  12. 2022Label Noise Robustness of Conformal Predictioncited by 20
5 more
  1. 2022JAWS: Auditing Predictive Uncertainty Under Covariate Shiftcited by 14
  2. 2021Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysiscited by 9
  3. 2019Spectrally-truncated kernel ridge regression and its free lunchcited by 4
  4. 2022Learning Invariant Representations under General Interventions on the Responsecited by 4
  5. 2024Low-Rank Approximation of Structural Redundancy for Self-Supervised Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 6.

8 papers.

  1. 2025Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coveragecited by 13
  2. 2026Anytime-Valid Conformal Risk Controlcited by 5
  3. 2026Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shiftscited by 4
  4. 2026Multi-Agent Conformal Prediction with Personalized Statistical Validitycited by 1
  5. 2026Sharp training-conditional coverage for conformal prediction under covariate shiftcited by 1
  6. 2024Distribution-Free Predictive Inference under Unknown Temporal Driftcited by 0
  7. 2026Softmax is not Enough (for Adaptive Conformal Classification)cited by 0
  8. 2026Conformal PM2.5 Mapping Under Spatial Covariate Shift: Satellite-Reanalysis Fusion for Africa's Green Industrial Transitioncited by 0