SOURCE-LINKED INTELLIGENCE

Calibration-Preserving Pruning: Compression as a Reliability Contract

arXiv · AI, language, vision and robotics · article · Aug 24, 2026 · UTC

Split conformal prediction, not the pruning rule, supplies finite-sample marginal coverage once a pruned model is fixed independently of the conformal calibration split. We study the separate efficiency problem: can pruning preserve score geometry well enough to obtain smaller valid prediction sets? Calibration-Preserving Pruning (CPP) augments a base pruning score with nonconformity-gradient saliency and uses disjoint pruning, validation-selection, conformal-calibration, and test splits. Bounded score perturbations imply bounded conformal-quantile shifts and controlled set inflation, but do n

Read original source ↗ Open in workspace

recordType

paper

region

Global