Search papers, labs, and topics across Lattice.
This paper introduces Calibration-Preserving Pruning (CPP), a method that enhances model pruning by incorporating nonconformity-gradient saliency to maintain score geometry and improve prediction set validity. The authors demonstrate that CPP effectively reduces the mean set size of predictions while achieving competitive accuracy across various datasets, notably achieving a reduction from 10.1 to 8.6 in mean set size on DBpedia-14 with an accuracy increase from 0.347 to 0.366. The results indicate that CPP can significantly enhance the efficiency of pruned models in reliability-sensitive classification tasks without compromising their calibration properties.
Pruning models can lead to smaller, more accurate prediction sets without sacrificing reliability, as shown by CPP's impressive performance on large-label tasks.
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 not make the generic coverage theorem CPP-specific. Final five-seed Qwen2.5-1.5B results at 50\% sparsity show the largest gains on large-label tasks. On DBpedia-14, CPP-SparseGPT reduces mean set size from \(10.1\) to \(8.6\) while changing accuracy from \(0.347\) to \(0.366\); CPP-Wanda reduces \(11.2\) to \(9.0\) with an accuracy trade-off from \(0.310\) to \(0.295\). Across 15 dataset--sparsity cells, CPP-SparseGPT produces smaller sets in 13 and higher accuracy in 11. Matched controls show that generic supervised gradients explain much of the gain: true-label CPP is not statistically resolved from matched Wanda+SNIP, whereas threshold-aware candidate-label CPP reaches \(7.8\) mean set size at explicit accuracy and offline-compute costs. RoBERTa-base and Llama-3-8B diagnostics support transfer, but our claims remain limited to reliability-sensitive classification.
