arXiv Machine Learning
Replicable Conformal Prediction
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
Aug 24
The Exceedance Design Effect: Effective Sample Size for Thresholds under Clustering
arXiv:2608.21262v1 Announce Type: cross Abstract: Many machine-learning systems set a threshold at a quantile of a calibration set: conformal predictors that promise 90% coverage by drawing their cut...
arXiv Machine Learning
Aug 26
Calibration-Preserving Pruning: Compression as a Reliability Contract
arXiv:2608.23744v1 Announce Type: new Abstract: Split conformal prediction, not the pruning rule, supplies finite-sample marginal coverage once a pruned model is fixed independently of the conformal...
arXiv Machine Learning
Jul 21
Isotonic Conformal Prediction
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.
arXiv Machine Learning
Jul 21
The Label Complexity of Class-Conditional Coverage under Distribution Shift
arXiv:2607. 18088v1 Announce Type: new Abstract: Standard evaluation of many recognition systems contains distribution shift by construction, since benchmarks place disjoint conditions in the training and test splits.
arXiv AI
Jun 30
Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery
arXiv:2606. 29403v1 Announce Type: cross Abstract: Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in safety-critical subgroups.
arXiv Machine Learning
Jun 3
Set-Preserving Calibration from Conformal P-Values to E-Values
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.