cs.LGMay 10, 2026

Selection Plateau and a Sparsity-Dependent Hierarchy of Pruning Features

Authors: Guangqi LiYongxin Li

Organizations: Zaozhuang University, Zaozhuang, Shandong, China

Abstract

We identify a Selection Plateau phenomenon in one-shot neural network pruning: all rank-monotone weight scorers converge to identical accuracy at fixed sparsity, independent of functional form. We propose the Sparsity-Information-Complexity Spectrum (SICS) hypothesis: a sparsity-dependent minimum feature complexity kappa(S) governs plateau escape, with kappa=0 sufficient at low sparsity (S<0.65), kappa=1 dominant at critical sparsity (S~0.7), and kappa=2 necessary at extreme sparsity (S>0.75). On ViT-Small/CIFAR-10, testing nine feature classes across four sparsities, smooth non-monotone features provide +6.6% escape at S=0.7, while only raw features with high-frequency wiggle escape at S=0.8 (+2.6%). A fake non-monotone scorer underperforms the gradient baseline, indicating the requirement is magnitude-independent non-monotonicity. A handcrafted Gaussian bump achieves only +0.006 escape vs. chaos-derived +0.046, indicating rank-alignment is necessary but insufficient. SICS provides a unifying explanation for the performance clustering of diverse pruning methods and suggests that future selection algorithms should adapt feature complexity to target sparsity.

Explore similar work

CardsList
  1. Functional Degeneracy in Neural Networks: Measurement and Pruning

    Aug 31, 2026Maria Matveev, Pascal Esser, Ayush Bharadwaj +2PruningNeural Network

  2. Pruning Deep Neural Networks via the Marchenko--Pastur Distribution

    May 23, 2026Leonid Berlyand, Theo Bourdais, Houman Owhadi +1Resnet-18