arXiv Machine Learning
Scaling Full Conformal Image Classifiers
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jul 1
Localized Conformal Prediction for Image Classification with Vision-Language Models
arXiv:2606. 31577v1 Announce Type: cross Abstract: Conformal predictions have attracted significant attention in the field of uncertainty quantification, mainly because of their strong marginal coverage guarantees.
arXiv Machine Learning
Jun 30
Conformal Prediction with Macro-Coverage Guarantees
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.
arXiv Machine Learning
Sep 15
Noise-Adaptive Conformal Classification with Marginal Coverage
arXiv:2501.18060v2 Announce Type: replace-cross Abstract: Conformal inference provides a rigorous statistical framework for uncertainty quantification in machine learning, enabling well-calibrated pr...
arXiv Machine Learning
Jun 11
Coverage Guarantees for Pseudo-Calibrated Conformal Prediction under Distribution Shift
arXiv:2602. 14913v2 Announce Type: replace Abstract: Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data distribution shifts.
arXiv Machine Learning
Sep 11
Benchmarking non-conformity score functions in conformal prediction
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.
arXiv Machine Learning
Jun 25
Adaptive Cumulative Mass Calibration with Conformal Prediction
arXiv:2505. 15437v3 Announce Type: replace-cross Abstract: Reliable probability estimates by classifiers are essential in high-risk applications.