Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kolb, Chris, Frost, Laetitia, Bischl, Bernd, Rügamer, David
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914113430487040
author Kolb, Chris
Frost, Laetitia
Bischl, Bernd
Rügamer, David
author_facet Kolb, Chris
Frost, Laetitia
Bischl, Bernd
Rügamer, David
contents Structured sparsity regularization offers a principled way to compact neural networks, but its non-differentiability breaks compatibility with conventional stochastic gradient descent and requires either specialized optimizers or additional post-hoc pruning without formal guarantees. In this work, we propose $D$-Gating, a fully differentiable structured overparameterization that splits each group of weights into a primary weight vector and multiple scalar gating factors. We prove that any local minimum under $D$-Gating is also a local minimum using non-smooth structured $L_{2,2/D}$ penalization, and further show that the $D$-Gating objective converges at least exponentially fast to the $L_{2,2/D}$-regularized loss in the gradient flow limit. Together, our results show that $D$-Gating is theoretically equivalent to solving the original group sparsity problem, yet induces distinct learning dynamics that evolve from a non-sparse regime into sparse optimization. We validate our theory across vision, language, and tabular tasks, where $D$-Gating consistently delivers strong performance-sparsity tradeoffs and outperforms both direct optimization of structured penalties and conventional pruning baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23898
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
Kolb, Chris
Frost, Laetitia
Bischl, Bernd
Rügamer, David
Machine Learning
Structured sparsity regularization offers a principled way to compact neural networks, but its non-differentiability breaks compatibility with conventional stochastic gradient descent and requires either specialized optimizers or additional post-hoc pruning without formal guarantees. In this work, we propose $D$-Gating, a fully differentiable structured overparameterization that splits each group of weights into a primary weight vector and multiple scalar gating factors. We prove that any local minimum under $D$-Gating is also a local minimum using non-smooth structured $L_{2,2/D}$ penalization, and further show that the $D$-Gating objective converges at least exponentially fast to the $L_{2,2/D}$-regularized loss in the gradient flow limit. Together, our results show that $D$-Gating is theoretically equivalent to solving the original group sparsity problem, yet induces distinct learning dynamics that evolve from a non-sparse regime into sparse optimization. We validate our theory across vision, language, and tabular tasks, where $D$-Gating consistently delivers strong performance-sparsity tradeoffs and outperforms both direct optimization of structured penalties and conventional pruning baselines.
title Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
topic Machine Learning
url https://arxiv.org/abs/2509.23898