mlsanityData to 7 Oct 2026

Predictive Inference Is Free with the Jackknife+-after-Bootstrap

arXiv 2002.09025 ↗First posted 20 Feb 2020stat.MEcited by 55

Not on the map. Why?

Abstract (arXiv)

Ensemble learning is widely used in applications to make predictions in complex decision problems---for example, averaging models fitted to a sequence of samples bootstrapped from the available training data. While such methods offer more accurate, stable, and robust predictions and model estimates, much less is known about how to perform valid, assumption-lean inference on the output of these types of procedures. In this paper, we propose the jackknife+-after-bootstrap (J+aB), a procedure for constructing a predictive interval, which uses only the available bootstrapped samples and their corresponding fitted models, and is therefore "free" in terms of the cost of model fitting. The J+aB offers a predictive coverage guarantee that holds with no assumptions on the distribution of the data, the nature of the fitted model, or the way in which the ensemble of models are aggregated---at worst, the failure rate of the predictive interval is inflated by a factor of 2. Our numerical experiments verify the coverage and accuracy of the resulting predictive intervals on real data.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 12; 2023: 8; 2024: 10; 2025: 10; 2026: 8.

55 papers.

Sort:

By area:

  1. 2021Testing for Outliers with Conformal p-valuescited by 133
  2. 2021Conformal Prediction using Conditional Histogramscited by 77
  3. 2024Conformal prediction for multi-dimensional time series by ellipsoidal setscited by 37
  4. 2023Conformal prediction under ambiguous ground truthcited by 31
  5. 2022Copula Conformal Prediction for Multi-step Time Series Forecastingcited by 28
  6. 2022Ensemble Conformalized Quantile Regression for Probabilistic Time Series Forecastingcited by 27
  7. 2022Split Localized Conformal Predictioncited by 20
  8. 2022Integrative conformal p-values for powerful out-of-distribution testing with labeled outlierscited by 19
  9. 2022MAPIE: an open-source library for distribution-free uncertainty quantificationcited by 17
  10. 2023Integrating Uncertainty Awareness into Conformalized Quantile Regressioncited by 17
  11. 2021Learning Prediction Intervals for Regression: Generalization and Calibrationcited by 16
  12. 2023Derandomized Novelty Detection with FDR Control via Conformal E-valuescited by 15
38 more
  1. 2023Conformal inference is (almost) free for neural networks trained with early stoppingcited by 14
  2. 2021Conformal Anomaly Detection on Spatio-Temporal Observations with Missing Datacited by 12
  3. 2024Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Modelscited by 12
  4. 2024Kernel-based Optimally Weighted Conformal Time-Series Predictioncited by 12
  5. 2022Conformal Methods for Quantifying Uncertainty in Spatiotemporal Data: A Surveycited by 11
  6. 2024Regression Trees for Fast and Adaptive Prediction Intervalscited by 11
  7. 2024Weighted Aggregation of Conformity Scores for Classificationcited by 11
  8. 2025PCS-UQ: Uncertainty Quantification via the Predictability-Computability-Stability Frameworkcited by 9
  9. 2025Full Conformal Adaptation of Medical Vision-Language Modelscited by 9
  10. 2021Root-finding Approaches for Computing Conformal Prediction Setcited by 8
  11. 2022Conformal Credal Self-Supervised Learningcited by 8
  12. 2024Conformal Risk Control for Ordinal Classificationcited by 8
  13. 2022Conformal prediction set for time-seriescited by 5
  14. 2022What's Behind the Mask: Estimating Uncertainty in Image-to-Image Problemscited by 5
  15. 2023Explanation Shift: How Did the Distribution Shift Impact the Model?cited by 5
  16. 2025Improving the statistical efficiency of cross-conformal predictioncited by 5
  17. 2025Extreme Conformal Prediction: Reliable Intervals for High-Impact Eventscited by 5
  18. 2022A Survey on Uncertainty Toolkits for Deep Learningcited by 4
  19. 2022Distribution-Free Finite-Sample Guarantees and Split Conformal Predictioncited by 4
  20. 2023Stability of Random Forests and Coverage of Random-Forest Prediction Intervalscited by 4
  21. 2024Leave-One-Out-, Bootstrap- and Cross-Conformal Anomaly Detectorscited by 4
  22. 2026Between Resolution Collapse and Variance Inflation: Weighted Conformal Anomaly Detection in Low-Data Regimescited by 4
  23. 2026Leave a Window Out: Modifying the Jackknife for Predictive Inference in Time Seriescited by 4
  24. 2021Time Series Anomaly Detection with label-free Model Selectioncited by 3
  25. 2024Conformal time series decomposition with component-wise exchangeabilitycited by 3
  26. 2025Conformal Object Detection by Sequential Risk Controlcited by 3
  27. 2025Sparse Identification of Nonlinear Dynamics with Conformal Predictioncited by 3
  28. 2023Conformalized Semi-supervised Random Forest for Classification and Abnormality Detectioncited by 2
  29. 2025iLOCO: Distribution-Free Inference for Feature Interactionscited by 2
  30. 2026Data-driven sparse identification of governing PDEs via knockoff filters and multi-criteria trade-offscited by 2
  31. 2022A general framework for multi-step ahead adaptive conformal heteroscedastic time series forecastingcited by 1
  32. 2024U-learning for Prediction Inference via Combinatory Multi-Subsampling: With Applications to LASSO and Neural Networkscited by 1
  33. 2025Uncertainty-Aware Prediction of Parkinson's Disease Medication Needs: A Two-Stage Conformal Prediction Approachcited by 1
  34. 2021Centroid Approximation for Bootstrap: Improving Particle Quality at Inferencecited by 0
  35. 2023Model Agnostic Explainable Selective Regression via Uncertainty Estimationcited by 0
  36. 2024Learning from Uncertain Data: From Possible Worlds to Possible Modelscited by 0
  37. 2025coverforest: Conformal Predictions with Random Forest in Pythoncited by 0
  38. 2025Centrum: Model-based Database Auto-tuning with Minimal Distributional Assumptionscited by 0

50 most cited of 55 All 55 (JSON)