mlsanityData to 13 Oct 2026

Robust Conditional Conformal Prediction via Branched Normalizing Flow

arXiv 2605.01868 ↗First posted 3 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Conformal prediction (CP) constructs prediction sets with marginal coverage guarantees under the assumption that the calibration and test distributions are identical. However, under distribution shift, existing approaches primarily align marginal conformal score distributions, which is sufficient to preserve marginal coverage but does not control the conditional coverage error at individual test inputs. As a consequence, CP can remain unreliable in regions where the conditional score distributions are mismatched. In this work, we bound the conditional invalidity of CP under distribution shift in terms of the Wasserstein distance between the calibration and test distributions. This result highlights the role of invertible transport in mitigating conditional coverage degradation. Motivated by this insight, we introduce Branched Normalizing Flow (BNF), a two-branch architecture that normalizes a test input to the calibration distribution and transforms the prediction set of the normalized input back to the test distribution while preserving conditional guarantees. Empirically, BNF consistently improves conditional coverage robustness on nine datasets across a wide range of confidence levels.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 45 of its 80 references that are in the map. First posted on arXiv 3 May 2026.

Builds on

45 of 80 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,870
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,295
  4. 2015Variational Inference with Normalizing Flowscited by 2,163
  5. 2016Density estimation using Real NVPcited by 2,033
  6. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,317
  7. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,242
  8. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 738
  9. 2016Distribution-Free Predictive Inference For Regressioncited by 660
  10. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 638
  11. 2019Conformalized Quantile Regressioncited by 625
  12. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 527
33 more
  1. 2019Conformal Prediction Under Covariate Shiftcited by 513
  2. 2020Classification with Valid and Adaptive Coveragecited by 393
  3. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 365
  4. 2022Conformal prediction beyond exchangeabilitycited by 351
  5. 2018Statistical Aspects of Wasserstein Distancescited by 202
  6. 2016Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Reviewcited by 155
  7. 2023Conformal Prediction With Conditional Guaranteescited by 150
  8. 2018Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecastingcited by 146
  9. 2021Localized Conformal Prediction: A Generalized Inference Framework for Conformal Predictioncited by 113
  10. 2021Learning Optimal Conformal Classifierscited by 109
  11. 2020Robust Validation: Confident Predictions Even When Distributions Shiftcited by 82
  12. 2019A comparison of some conformal quantile regression methodscited by 76
  13. 2021Domain Adaptation for Time Series Forecasting via Attention Sharingcited by 68
  14. 2020Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Modelscited by 66
  15. 2014Regression Conformal Prediction with Nearest Neighbourscited by 59
  16. 2019Adaptive, Distribution-Free Prediction Intervals for Deep Networkscited by 56
  17. 2023normflows: A PyTorch Package for Normalizing Flowscited by 56
  18. 2021Improving Conditional Coverage via Orthogonal Quantile Regressioncited by 48
  19. 2021Selection and Aggregation of Conformal Prediction Setscited by 47
  20. 2023Federated Conformal Predictors for Distributed Uncertainty Quantificationcited by 46
  21. 2020The Expressive Power of a Class of Normalizing Flow Modelscited by 35
  22. 2023Adaptive conformal classification with noisy labelscited by 25
  23. 2021Locally Valid and Discriminative Prediction Intervals for Deep Learning Modelscited by 24
  24. 2025Multivariate Conformal Prediction using Optimal Transportcited by 22
  25. 2024An Information Theoretic Perspective on Conformal Predictioncited by 21
  26. 2025Wasserstein-regularized Conformal Prediction under General Distribution Shiftcited by 15
  27. 2024On Temperature Scaling and Conformal Prediction of Deep Classifierscited by 13
  28. 2024Does confidence calibration improve conformal prediction?cited by 12
  29. 2024Normalizing Flows for Conformal Regressioncited by 11
  30. 2025On Volume Minimization in Conformal Regressioncited by 9
  31. 2025Parametric Scaling Law of Tuning Bias in Conformal Predictioncited by 7
  32. 2024Coverage-Guaranteed Prediction Sets for Out-of-Distribution Datacited by 5
  33. 2025Distributed Conformal Prediction via Message Passingcited by 4

Built on by

Not cited yet.