# SHUFFLESPARSE: Learned Shuffles for Structured Sparse Networks

arXiv: https://arxiv.org/abs/2510.14812 · HTML: https://mlsanity.com/paper/2510.14812/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 30 of 33)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [On the Number of Linear Regions of Deep Neural Networks](https://mlsanity.com/paper/1402.1869/) (2014)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [Accelerating Sparse Deep Neural Networks](https://mlsanity.com/paper/2104.08378/) (2021)
- [Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization](https://mlsanity.com/paper/1902.05967/) (2019)
- [DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs](https://mlsanity.com/paper/2406.01721/) (2024)
- [Towards Optimal Structured CNN Pruning via Generative Adversarial Learning](https://mlsanity.com/paper/1903.09291/) (2019)
- [RPTQ: Reorder-based Post-training Quantization for Large Language Models](https://mlsanity.com/paper/2304.01089/) (2023)
- [Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks](https://mlsanity.com/paper/2102.08124/) (2021)
- [MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge](https://mlsanity.com/paper/2110.14032/) (2021)
- [Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models](https://mlsanity.com/paper/2112.00029/) (2021)
- [SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models](https://mlsanity.com/paper/2405.06219/) (2024)
- [Dynamic Sparse Training with Structured Sparsity](https://mlsanity.com/paper/2305.02299/) (2023)
- [Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps](https://mlsanity.com/paper/2012.14966/) (2020)
- [AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models](https://mlsanity.com/paper/2410.10912/) (2024)
- [Training Your Sparse Neural Network Better with Any Mask](https://mlsanity.com/paper/2206.12755/) (2022)
- [AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1901.08624/) (2019)
- [On improving deep learning generalization with adaptive sparse connectivity](https://mlsanity.com/paper/1906.11626/) (2019)

## Abstract (arXiv)

Structured weight sparsity accelerates training and inference on modern GPUs, but it trails unstructured dynamic sparse training (DST) in accuracy especially at extreme sparsity. We pinpoint the reason for this difference in performance to a lack of expressivity: a dense layer can implement any pattern of non-zero weights, whereas structured patterns are restricted to only a small set of weight configurations. We introduce SHUFFLESPARSE, a single permutation primitive that applies uniformly across DST-from-scratch and one-shot pruning, and across N:M, block etc. We close most of this gap by learning a single permutation matrix jointly with the structured weight matrix. When used on three different types of structures (block, N:M, and diagonal), SHUFFLESPARSE is able to reduce the structured-vs-unstructured accuracy gap on ViT-B16 (ImageNet-1K) and GPT-2 (WikiText-103) at 90-95% sparsity, while adding minimal inference overhead (< 8.7% inference overhead) and preserving any training acceleration the host structure provides. The same permutation formulation transfers to one-shot 2:4 pruning of pretrained LLMs, where it improves zero-shot accuracy by 4.6 points on LLaMA-2 7B. Together, these results establish learned permutations as a general tool for recovering unstructured-level accuracy from structured sparsity patterns.