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

MCML Authors

Chris Kolb

Dr.

→ Group David Rügamer
 Statistics, Data Science and Machine Learning

Bernd Bischl

Prof. Dr.

Director

Statistical Learning and Data Science

David Rügamer

Prof. Dr.

Core PI

Statistics, Data Science and Machine Learning

Abstract

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 L2,2/D penalization, and further show that the D-Gating objective converges at least exponentially fast to the L2,2/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.

inproceedings KFB+25

---

NeurIPS 2025

39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. Spotlight Presentation.

---

Authors

C. Kolb • L. Frost • B. Bischl • D. Rügamer

---

Links

URL

---

Research Area

 A1 | Statistical Foundations & Explainability