AI RESEARCH
Relative Repairability: A Calibration-Based Diagnostic for High-Sparsity Post-Pruning Allocation
arXiv CS.LG
•
ArXi:2605.25508v1 Announce Type: new At very high sparsity, neural network pruning does than decide which weights remain. It also determines where pruning induced damage is placed across the network, and whether that damage can be recovered by a fixed lightweight repair procedure. We study this problem through the lens of repair conditioned sparsity allocation. We