Structural pruning enhances hardware-agnostic inference efficiency for large language models (LLMs) yet often fails to maintain comparable performance. Local pruning performs efficient layer-by-layer compression but ignores global topology. Although global pruning aims to identify an optimal sparse model, intuitive methods typically adopt a two-stage paradigm that first evaluates substructure saliency and then applies global pruning, which ignores inter-structure dependencies and fails to achieve end-to-end optimization. To address these limitations, we propose Týr-the-Pruner, an efficient end-to-end search-based global structural pruning framework. This framework constructs a supernet by repeatedly applying local pruning across a range of sparsity ratios to each layer in an LLM, with the core goal of determining the optimal sparsity distribution under a target overall sparsity ratio. Concretely, we introduce an effective local pruning and an expectation error accumulation approach to improve supernet construction. Furthermore, we employ an iterative prune-and-search strategy with coarse-to-fine sparsity granularity to ensure efficient search convergence. Experimental results show that Týr-the-Pruner achieves state-of-the-art structural pruning, retaining 97% of the dense model's performance while removing a challenging 50% of Llama-3.1-70B's parameters. Code will be available at https://github.com/AMD-AGI/Tyr-the-Pruner.
Z-Pruner: Post-Training Pruning of Large Language Models for Efficiency without Retraining
Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh（电气与计算机工程系，北南大学，达卡，孟加拉国）；Data Science and AI, University of Doha for Science and Technology, Doha, Qatar（数据科学与人工智能，多哈科学技术大学，多哈，卡塔尔）
Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；Hong Kong Baptist Univeristy（香港浸会大学）；Harbin Institude of Technology, Shenzhen（哈尔滨工业大学（深圳））
FAIR-Pruner: A Flexible Framework for Automatic Layer-Wise Pruning via Tolerance of Difference
School of Statistics and Mathematics, Zhejiang Gongshang University（浙江工商大学统计与数学学院）；École de technologie supérieure (ÉTS), Université du Québec（魁北克大学埃克森技术学院）；Southern University of Science and Technology（南方科技大学）
Technical University of Vienna（维也纳技术大学）；MIT（麻省理工学院）
In this paper, we present a novel sensitivity-based filter pruning algorithm (SbF-Pruner) to learn the importance scores of filters of each layer end-to-end. Our method learns the scores from the filter weights, enabling it to account for the correlations between the filters of each layer. Moreover, by training the pruning scores of all layers simultaneously our method can account for layer interdependencies, which is essential to find a performant sparse sub-network. Our proposed method can train and generate a pruned network from scratch in a straightforward, one-stage training process witho…
We present a filter pruning approach for deep model compression, using a multitask network. Our approach is based on learning a a pruner network to prune a pre-trained target network. The pruner is essentially a multitask deep neural network with binary outputs that help identify the filters from each layer of the original network that do not have any significant contribution to the model and can therefore be pruned. The pruner network has the same architecture as the original network except that it has a multitask/multi-output last layer containing binary-valued outputs (one per filter), whic…
Ostfalia University of Applied Sciences（东法利亚应用科学大学）；Clausthal University of Technology（克劳斯塔尔工业大学）；Helmholtz Centre for Infection Research（亥姆霍兹感染研究中心）
Background: Embedded feature selection in high-dimensional data with very small sample sizes requires optimized hyperparameters for the model building process. For this hyperparameter optimization, nested cross-validation must be applied to avoid a biased performance estimation. The resulting repeated training with high-dimensional data leads to very long computation times. Moreover, it is likely to observe a high variance in the individual performance evaluation metrics caused by outliers in tiny validation sets. Therefore, early stopping applying standard pruning algorithms to save time risk…
Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization
Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi（德里印度理工学院亚迪人工智能学院）；Indian Institute of Technology Delhi（德里印度理工学院）；Microsoft Research (MSR) India（微软研究院印度分部）
Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance. However, without a clear consensus on "how to choose," the layerwise sparsities are mostly selected algorithm-by-algorithm, often resorting to handcrafted heuristics or an extensive hyperparameter search. To fill this gap, we propose a novel importance score for global pruning, coined layer-adaptive magnitude-based pruning (LAMP) score; the score is a rescaled version of weight magnitude that …
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
Eindhoven University of Technology, the Netherlands（埃因霍温理工大学）；University of Surrey（萨里大学）；Google Research, USA（谷歌研究院）；University of Texas at Austin, USA（德克萨斯大学奥斯汀分校）；Clemson University, USA（克莱姆森大学）；University of Washington, USA（华盛顿大学）；University of Oxford, UK（牛津大学）
Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural language processing applications. We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. We give mathematical foundations to the method and compare it to existing zeroth- and first-order pruning methods. Experiments show that when pruning large pretrained language models, movement pruning…
EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；University of Oxford（牛津大学）；Peking University（北京大学）
Mila, McGill University（麦吉尔大学 Mila 研究院）；Georgia Institute of Technology（佐治亚理工学院）；Georgia State University（佐治亚州立大学）；DeepMind
Deep Reinforcement Learning (RL) is a powerful framework for solving complex real-world problems. Large neural networks employed in the framework are traditionally associated with better generalization capabilities, but their increased size entails the drawbacks of extensive training duration, substantial hardware resources, and longer inference times. One way to tackle this problem is to prune neural networks leaving only the necessary parameters. State-of-the-art concurrent pruning techniques for imposing sparsity perform demonstrably well in applications where data distributions are fixed. …
Bucknell University（巴克内尔大学）；University of Utah（犹他大学）
One surprising trait of neural networks is the extent to which their connections can be pruned with little to no effect on accuracy. But when we cross a critical level of parameter sparsity, pruning any further leads to a sudden drop in accuracy. This drop plausibly reflects a loss in model complexity, which we aim to avoid. In this work, we explore how sparsity also affects the geometry of the linear regions defined by a neural network, and consequently reduces the expected maximum number of linear regions based on the architecture. We observe that pruning affects accuracy similarly to how sp…
Budgeted pruning is the problem of pruning under resource constraints. In budgeted pruning, how to distribute the resources across layers (i.e., sparsity allocation) is the key problem. Traditional methods solve it by discretely searching for the layer-wise pruning ratios, which lacks efficiency. In this paper, we propose Differentiable Sparsity Allocation (DSA), an efficient end-to-end budgeted pruning flow. Utilizing a novel differentiable pruning process, DSA finds the layer-wise pruning ratios with gradient-based optimization. It allocates sparsity in continuous space, which is more effici…
Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks
Department of Mathematical and Statistical Sciences, Marquette University（马歇尔大学数学与统计科学系）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Cornell Ann S. Bowers College of Computing and Information Science, Cornell University（康奈尔大学安·S·博尔斯计算与信息科学学院）
Pruning neural networks has regained interest in recent years as a means to compress state-of-the-art deep neural networks and enable their deployment on resource-constrained devices. In this paper, we propose a robust compressive learning framework that efficiently prunes network parameters during training with minimal computational overhead. We incorporate fast mechanisms to prune individual layers and build upon these to automatically prune the entire network under a user-defined budget constraint. Key to our end-to-end network pruning approach is the formulation of an intuitive and easy-to…
Hasso Plattner Institute for Digital Health at the Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院哈索·普拉特纳数字健康研究所）；Hasso Plattner Institute for Digital Engineering, University of Potsdam（波茨坦大学哈索·普拉特纳数字工程研究所）；Google DeepMind（谷歌DeepMind）
Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) while maintaining accuracy. Most available filter pruning methods require complex treatments such as iterative pruning, features statistics/ranking, or additional optimization designs in the training process. In this paper, we propose a simple and effective regularization strategy from a new perspective of evolution of features, which we call feature flow regularization (FFR), for improving structured sparsity and filter pruning in DNNs. Specifically, FFR imposes controls on the gradient and …
In recent years, there has been a flurry of research in deep neural network pruning and compression. Early approaches prune weights individually. However, it is difficult to take advantage of the resulting unstructured sparsity patterns on modern hardware like GPUs. As a result, pruning strategies which impose sparsity structures in the weights have become more popular. However,these structured pruning approaches typically lead to higher losses in accuracy than unstructured pruning. In this paper, we present SparseRT, a code generator that leverage unstructured sparsity to accelerate sparse li…
Network pruning has been known to produce compact models without much accuracy degradation. However, how the pruning process affects a network's robustness and the working mechanism behind remain unresolved. In this work, we theoretically prove that the sparsity of network weights is closely associated with model robustness. Through experiments on a variety of adversarial pruning methods, we find that weights sparsity will not hurt but improve robustness, where both weights inheritance from the lottery ticket and adversarial training improve model robustness in network pruning. Based on these …
Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；University of Jeddah（吉达大学）；King Fahd University of Petroleum and Minerals（法赫德国王石油矿产大学）；King Saud University（沙特国王大学）
Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models
School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；Suzhou Institute for Advanced Research, University of Science and Technology of China（中国科学技术大学苏州高等研究院）
