# Testing RadiX-Nets: Advances in Viable Sparse Topologies

arXiv: https://arxiv.org/abs/2311.03609 · HTML: https://mlsanity.com/paper/2311.03609/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 6 Nov 2023.

## Builds on (most cited first, 10 of 10)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [The Power of Depth for Feedforward Neural Networks](https://mlsanity.com/paper/1512.03965/) (2015)
- [Faster gaze prediction with dense networks and Fisher pruning](https://mlsanity.com/paper/1801.05787/) (2018)
- [The Difficulty of Training Sparse Neural Networks](https://mlsanity.com/paper/1906.10732/) (2019)
- [Efficient Saliency Maps for Explainable AI](https://mlsanity.com/paper/1911.11293/) (2019)
- [Deep Expander Networks: Efficient Deep Networks from Graph Theory](https://mlsanity.com/paper/1711.08757/) (2017)
- [Understanding symmetries in deep networks](https://mlsanity.com/paper/1511.01029/) (2015)
- [RadiX-Net: Structured Sparse Matrices for Deep Neural Networks](https://mlsanity.com/paper/1905.00416/) (2019)
- [Training Behavior of Sparse Neural Network Topologies](https://mlsanity.com/paper/1810.00299/) (2018)
- [Exploring Gradient Flow Based Saliency for DNN Model Compression](https://mlsanity.com/paper/2110.12477/) (2021)

## Built on by (most cited first, 1 of 1)

- [Complexity of One-Dimensional ReLU DNNs](https://mlsanity.com/paper/2512.08091/) (2025)

## Abstract (arXiv)

The exponential growth of data has sparked computational demands on ML research and industry use. Sparsification of hyper-parametrized deep neural networks (DNNs) creates simpler representations of complex data. Past research has shown that some sparse networks achieve similar performance as dense ones, reducing runtime and storage. RadiX-Nets, a subgroup of sparse DNNs, maintain uniformity which counteracts their lack of neural connections. Generation, independent of a dense network, yields faster asymptotic training and removes the need for costly pruning. However, little work has been done on RadiX-Nets, making testing challenging. This paper presents a testing suite for RadiX-Nets in TensorFlow. We test RadiX-Net performance to streamline processing in scalable models, revealing relationships between network topology, initialization, and training behavior. We also encounter "strange models" that train inconsistently and to lower accuracy while models of similar sparsity train well.