Conformal prediction sets, which provide finite‑sample coverage guarantees, are examined from an information‑theoretic perspective. The authors introduce a family of generalized information measures that link set size and coverage to entropy, showing that Shannon mutual information can be expressed exactly in terms of these measures. They prove that, in classification tasks, the reduction in set size due to additional information is bounded by calibration‑dependent members of this family and satisfies a data‑processing inequality, and they empirically demonstrate that set‑size reduction and mutual information can rank features differently in greedy selection.
By Kevin Zhang, Stephen Bates
The paper extends conformal prediction by introducing a geometric view of uncertainty through credal sets, which are families of probability distributions compatible with CP regions. It provides analytical characterisations and efficient algorithms for common credal uncertainty measures, reducing complexity from exponential to linear after sorting p-values. The authors also unify these measures with classical conformal summaries using Tsallis entropy penalties, prove an impossibility theorem for split-conformal regression, and demonstrate through experiments that the new summaries recover ranking information lost by prediction-set size, enabling finer-grained uncertainty assessment.
By Siu Lun Chau, Soroush H. Zargarbashi, Yusuf Sale, Michele Caprio
arXiv:2505. 19033v2 Announce Type: replace-cross Abstract: Conformal prediction (CP) is a widely used frequentist framework to quantify uncertainty by constructing prediction sets with user-specified marginal coverage guarantees.
By Alireza Javanmardi, Soroush H. Zargarbashi, Santo M. A. R. Thies, Willem Waegeman, Aleksandar Bojchevski, Eyke H\"ullermeier
arXiv:2606. 03600v1 Announce Type: cross Abstract: Standard conformal prediction (CP) procedures are typically formulated in terms of p-values, but reliance on p-values alone limits flexibility, for example, when combining dependent evidence across models or data splits.
By Nabil Alami, Jad Zakharia, Souhaib Ben Taieb
arXiv:2509. 04631v2 Announce Type: replace Abstract: Transductive conformal prediction addresses the simultaneous prediction for multiple data points.
By Arash Behboodi, Alvaro H. C. Correia, Fabio Valerio Massoli, Christos Louizos
arXiv:2607. 16675v1 Announce Type: cross Abstract: A point prediction that is well calibrated on average can still be systematically biased conditional on its own value, undermining its use in downstream decision-making.
By Daniel Bensimon, Sean Xiang Yu, Eric D. Kolaczyk, Archer Y. Yang
arXiv:2606. 28598v1 Announce Type: cross Abstract: Prediction sets should have high coverage to be useful, but some coverage notions are more practically relevant than others.
By Aabesh Bhattacharyya, Tiffany Ding, Rina Foygel Barber
arXiv:2511.15146v2 Announce Type: replace
Abstract: Conformal prediction (CP) constructs uncertainty sets for model outputs with finite-sample coverage guarantees. Yet ranking scores is straightforwa...
By Eugene Ndiaye
arXiv:2606. 31600v1 Announce Type: cross Abstract: Conformal prediction and its variants, including the split conformal prediction, provide a distribution-free framework for uncertainty quantification by constructing prediction intervals or sets with finite-sample coverage guarantees.
By Sayan Das, Bahram Yaghooti, Todd A. Kuffner, Soumendra N. Lahiri
Conformal prediction replaces single-class predictions with prediction sets that guarantee a pre-specified coverage probability. The paper reviews properties of non‑conformity score functions, presents examples from the literature, and proposes new modifications. It introduces a method to evaluate prediction set sizes and compares different score functions, including their effectiveness for class‑conditional conformal prediction with imbalanced classes.
By Sol Erika Boman
A central question in modern learning theory is what notion of compression, if any, explains why over-parameterized neural networks generalize. Existing answers measure complexity at different levels,...
The paper investigates whether compression explains why over‑parameterized neural networks generalize, using the minimum description length (MDL) principle. It introduces prequential regret, a computable metric from the training trajectory, and shows that in the nearly interpolating regime it upper‑bounds the description length of the trained parameters, leading to a high‑probability generalization bound in the PAC‑MDL setting. The study also connects MDL with the algorithm‑level information bottleneck by bounding encoder‑complexity correction with MDL parameter description length, and demonstrates that prequential regret correlates strongly (Pearson > 0.9) with generalization error on CIFAR‑10 and CIFAR‑100.
By Lincen Yang, Jiayang Shi, Nan Pu, Dani\"el M. Pelt, Matthijs van Leeuwen, Zhong Li, Shujian Yu