# RadiX-Net: Structured Sparse Matrices for Deep Neural Networks

arXiv: https://arxiv.org/abs/1905.00416 · HTML: https://mlsanity.com/paper/1905.00416/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2019.

## Built on by (most cited first, 12 of 12)

- [The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training](https://mlsanity.com/paper/2202.02643/) (2022)
- [Selfish Sparse RNN Training](https://mlsanity.com/paper/2101.09048/) (2021)
- [Truly Sparse Neural Networks at Scale](https://mlsanity.com/paper/2102.01732/) (2021)
- [Sparse Training Theory for Scalable and Efficient Agents](https://mlsanity.com/paper/2103.01636/) (2021)
- [Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance](https://mlsanity.com/paper/2203.02770/) (2022)
- [Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training](https://mlsanity.com/paper/2205.15322/) (2022)
- [Partitioning sparse deep neural networks for scalable training and inference](https://mlsanity.com/paper/2104.11805/) (2021)
- [Pruning Before Training May Improve Generalization, Provably](https://mlsanity.com/paper/2301.00335/) (2023)
- [Sparsifying the Update Step in Graph Neural Networks](https://mlsanity.com/paper/2109.00909/) (2021)
- [REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training](https://mlsanity.com/paper/2312.03044/) (2023)
- [Testing RadiX-Nets: Advances in Viable Sparse Topologies](https://mlsanity.com/paper/2311.03609/) (2023)
- [Complexity of One-Dimensional ReLU DNNs](https://mlsanity.com/paper/2512.08091/) (2025)

## Abstract (arXiv)

The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after training by pruning edges from the underlying topology. The resulting neural network is known as a sparse neural network. More recent work has demonstrated the remarkable result that certain sparse DNNs can train to the same precision as dense DNNs at lower runtime and storage cost. An intriguing class of these sparse DNNs is the X-Nets, which are initialized and trained upon a sparse topology with neither reference to a parent dense DNN nor subsequent pruning. We present an algorithm that deterministically generates RadiX-Nets: sparse DNN topologies that, as a whole, are much more diverse than X-Net topologies, while preserving X-Nets' desired characteristics. We further present a functional-analytic conjecture based on the longstanding observation that sparse neural network topologies can attain the same expressive power as dense counterparts