cs.LGNov 18, 2026

SoU-RHS: Bayesian Structured Sparsity for Compact Architecture Recovery in CNNs

Authors: Rafael Mouallem Rosa, Julyan Arbel

Organizations: STATIFY · Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, 38000 Grenoble, France

Abstract

Highly parameterized convolutional neural networks often achieve strong predictive performance, but their memory, computation, and deployment costs motivate the search for methods that recover compact architectures from large reference models. We propose SoU-RHS, a Bayesian structured-sparsity procedure that augments Regularized Horseshoe Shrinkage (RHS) with the so-called Sources of Uncertainty Sparse Global-Local mechanism (SoU-SGL). The resulting model sharpens the separation between active and inactive filters, providing an effective mechanism for architecture recovery. A key property of SoU-RHS is stability: across different overparameterized starting widths and under a reasonable range of pruning thresholds, it recovers compact architectures with similar total size and layer-wise allocation. This supports the interpretation that the procedure is identifying a compact structure adapted to the data, rather than merely compressing each initial model separately. Across standard image-classification benchmarks, SoU-RHS recovers substantially smaller architectures than deterministic structured-sparsity baselines, while maintaining competitive accuracy, achieving lower negative log-likelihood in every evaluated configuration and generally lower expected calibration error.

Explore similar work

CardsList
  1. BaCP: Backbone Contrastive Pruning for Preserving Representations in Extremely Sparse Neural Networks

    Oct 1, 2026Mohammad Haroon Khawaja, Muhammad Haseeb, Mohammad Fatim Shoaib +1Neural Network PruningSparse Neural Networks

  2. Structured Channel Network Pruning with Bi-Sparse Matrix Factorization

    Oct 31, 2026Jingjing Liu, Ziyang Wang, Xianchao Xiu +1Channel PruningNeural Network Pruning