# A Proximal Operator for Inducing 2:4-Sparsity

arXiv: https://arxiv.org/abs/2501.18015 · HTML: https://mlsanity.com/paper/2501.18015/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 29 Jan 2025.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning](https://mlsanity.com/paper/2310.06694/) (2023)
- [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://mlsanity.com/paper/2401.15024/) (2024)
- [Compact Language Models via Pruning and Knowledge Distillation](https://mlsanity.com/paper/2407.14679/) (2024)
- [Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks](https://mlsanity.com/paper/2102.08124/) (2021)
- [Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs](https://mlsanity.com/paper/2310.08915/) (2023)
- [MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models](https://mlsanity.com/paper/2408.11743/) (2024)
- [MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models](https://mlsanity.com/paper/2409.17481/) (2024)
- [Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models](https://mlsanity.com/paper/2406.02924/) (2024)
- [A Survey of Techniques for Optimizing Transformer Inference](https://mlsanity.com/paper/2307.07982/) (2023)
- [Accuracy is Not All You Need](https://mlsanity.com/paper/2407.09141/) (2024)
- [ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models](https://mlsanity.com/paper/2406.07831/) (2024)
- [Inference Optimization of Foundation Models on AI Accelerators](https://mlsanity.com/paper/2407.09111/) (2024)

## Built on by (most cited first, 4 of 4)

- [ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs](https://mlsanity.com/paper/2502.00258/) (2025)
- [When LLMs get significantly worse: A statistical approach to detect model degradations](https://mlsanity.com/paper/2602.10144/) (2026)
- [UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs](https://mlsanity.com/paper/2510.03291/) (2025)
- [Achieving Linear Speedup for Composite Federated Learning](https://mlsanity.com/paper/2602.03357/) (2026)

## Abstract (arXiv)

Recent hardware advancements in AI Accelerators and GPUs allow to efficiently compute sparse matrix multiplications, especially when 2 out of 4 consecutive weights are set to zero. However, this so-called 2:4 sparsity usually comes at a decreased accuracy of the model. We derive a regularizer that exploits the local correlation of features to find better sparsity masks in trained models. We minimize the regularizer jointly with a local squared loss by deriving the proximal operator for which we show that it has an efficient solution in the 2:4-sparse case. After optimizing the mask, we use maskedgradient updates to further minimize the local squared loss. We illustrate our method on toy problems and apply it to pruning entire large language models up to 70B parameters. On models up to 13B we improve over previous state of the art algorithms, whilst on 70B models we match their performance.