mlsanityData to 14 Oct 2026

Conformal Correction for Efficiency May be at Odds with Entropy

arXiv 2512.02704 ↗First posted 2 Dec 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Conformal prediction (CP) provides a comprehensive framework to produce statistically rigorous uncertainty sets for black-box machine learning models. To further improve the efficiency of CP, conformal correction is proposed to fine-tune or wrap the base model with an extra module using a conformal-aware inefficiency loss. In this work, we empirically and theoretically identify a trade-off between the CP efficiency and the entropy of model prediction. We then propose an entropy-constrained conformal correction method, exploring a better Pareto optimum between efficiency and entropy. Extensive experimental results on both computer vision and graph datasets demonstrate the efficacy of the proposed method. For instance, it can significantly improve the efficiency of state-of-the-art CP methods by up to 34.4%, given an entropy threshold.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 43 references that are in the map. First posted on arXiv 2 Dec 2025.

Builds on

35 of 43 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2017On Calibration of Modern Neural Networkscited by 4,960
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  7. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  8. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  9. 2019Simplifying Graph Convolutional Networkscited by 1,477
  10. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  11. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  12. 2015Image-based Recommendations on Styles and Substitutescited by 706
23 more
  1. 2019Conformalized Quantile Regressioncited by 629
  2. 2020Classification with Valid and Adaptive Coveragecited by 396
  3. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
  4. 2020Calibrating Deep Neural Networks using Focal Losscited by 357
  5. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 272
  6. 2019Predictive inference with the jackknife+cited by 211
  7. 2020Fast Differentiable Sorting and Rankingcited by 197
  8. 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 139
  9. 2020Conformal Prediction: a Unified Review of Theory and New Challengescited by 118
  10. 2021Learning Optimal Conformal Classifierscited by 112
  11. 2013A Conformal Prediction Approach to Explore Functional Datacited by 86
  12. 2023Uncertainty Quantification over Graph with Conformalized Graph Neural Networkscited by 79
  13. 2022Training Uncertainty-Aware Classifiers with Conformalized Deep Learningcited by 64
  14. 2022Improving Expert Predictions with Conformal Predictioncited by 54
  15. 2023Conformal Prediction for Deep Classifier via Label Rankingcited by 53
  16. 2024Length Optimization in Conformal Predictioncited by 39
  17. 2024Conformal Prediction Sets Improve Human Decision Makingcited by 35
  18. 2022On the Utility of Prediction Sets in Human-AI Teamscited by 34
  19. 2022Predictive Inference with Feature Conformal Predictioncited by 34
  20. 2021Differentiable Sorting Networks for Scalable Sorting and Ranking Supervisioncited by 31
  21. 2023Designing Decision Support Systems Using Counterfactual Prediction Setscited by 26
  22. 2024An Information Theoretic Perspective on Conformal Predictioncited by 21
  23. 2024On Temperature Scaling and Conformal Prediction of Deep Classifierscited by 13

Built on by

Not cited yet.