arXiv Machine Learning
Calibration-Preserving Pruning: Compression as a Reliability Contract
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
4d ago
Rethinking Calibration for High-Sparsity LLM Pruning: From Single Sources to Capability Coverage
The paper argues that post‑training pruning of large language models should use a calibration set that covers multiple capability domains rather than a single source. A balanced four‑way mixture of sources consistently outperforms any single source across sparsity levels, model scales, and held‑out benchmarks. When aligned corpora are unavailable, the IGSP method approximates this mixture using only the base model and an evaluation taxonomy, achieving significant gains over prior self‑generation approaches.
arXiv Computation and Language
Sep 28
RAZOR: Pruning Replaceable Experts in LLMs
arXiv:2609.30465v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) models activate few experts per token but store the full expert pool. Expert pruning reduces this storage burden; at a fixed...
arXiv Machine Learning
Sep 1
PruneShift: A Framework for Evaluating Decision Reliability in Structured Pruning
arXiv:2608.29765v1 Announce Type: new Abstract: Structured pruning uses surrogate objectives because direct task evaluation over every feasible mask is too expensive. Most evaluations report average...
arXiv Machine Learning
Aug 26
Replicable Conformal Prediction
arXiv:2608.23638v1 Announce Type: cross Abstract: Two analysts who calibrate the same predictive model on independent samples will deploy different prediction sets every time, because the calibration...
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 Machine Learning
Jul 31
Averaged Evaluation Masks Capability Trade-Offs: Multi-Source Calibration for High-Sparsity LLM Pruning
arXiv:2606. 03328v3 Announce Type: replace Abstract: Calibration data are often treated as a minor implementation detail in post-training LLM pruning because averaged evaluations suggest only modest effects.