English
Related papers

Related papers: AIRE-Prune: Asymptotic Impulse-Response Energy for…

200 papers

Training deep neural networks (DNNs) is costly. Fortunately, Nvidia Ampere and Hopper GPUs can accelerate matrix multiplications twice as fast as a dense equivalent by implementing 2:4 sparsity. However, previous STE-based 2:4 pre-training…

Machine Learning · Computer Science 2024-12-30 Yuezhou Hu , Jun Zhu , Jianfei Chen

Model pruning is a performance optimization technique for large language models like R1 or o3-mini. However, existing pruning methods often lead to significant performance degradation or require extensive retraining and fine-tuning. This…

Computation and Language · Computer Science 2025-05-21 Wei Jiang , Anying Fu , Youling Zhang

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…

Computation and Language · Computer Science 2020-10-26 Victor Sanh , Thomas Wolf , Alexander M. Rush

We challenge the conventional view of neural network pruning as solely a compression technique, demonstrating that one-shot magnitude pruning serves as a powerful implicit regularizer for ASR. Using Whisper-small, we combine gradient- and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-12 Julian Irigoyen , Arthur Söhler , Andreas Søeborg Kirkedal

Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-training sparsity (PTS), which reduces model cost by removing…

Computation and Language · Computer Science 2026-02-26 Minhao Jiang , Zhikai Li , Xuewen Liu , Jing Zhang , Mengjuan Chen , Qingyi Gu

IoT and edge-based inference systems require unique solutions to overcome resource limitations and unpredictable environments. In this paper, we propose an environment-aware dynamic pruning system that handles the unpredictability of edge…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-06 Austin O'Quinn , Conor Snedeker , Siyuan Zhang , Jenna Kline

Attention-based architectures have achieved superior performance in multivariate time series forecasting but are computationally expensive. Techniques such as patching and adaptive masking have been developed to reduce their sizes and…

Machine Learning · Computer Science 2025-05-14 Suhan Guo , Jiahong Deng , Mengjun Yi , Furao Shen , Jian Zhao

With the rise in interest of sparse neural networks, we study how neural network pruning with synthetic data leads to sparse networks with unique training properties. We find that distilled data, a synthetic summarization of the real data,…

Machine Learning · Computer Science 2025-04-15 Luke McDermott , Daniel Cummings

Convolutional Neural Networks (CNNs) are hard to deploy on edge devices due to its high computation and storage complexities. As a common practice for model compression, network pruning consists of two major categories: unstructured and…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Yuchuan Tian , Hanting Chen , Tianyu Guo , Chao Xu , Yunhe Wang

Energy efficient implementations and deployments of Spiking neural networks (SNNs) have been of great interest due to the possibility of developing artificial systems that can achieve the computational powers and energy efficiency of the…

Machine Learning · Computer Science 2023-02-09 Clemens JS Schaefer , Pooria Taheri , Mark Horeni , Siddharth Joshi

Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency costs. We present GRASPrune, a structured pruning framework applied after pretraining…

Artificial Intelligence · Computer Science 2026-04-22 Ziyang Wang , Jiangfeng Xiao , Chuan Xiao , Ruoxiang Li , Rui Mao , Jianbin Qin

Empirical scaling laws for language models have encouraged the development of ever-larger LLMs, despite their growing computational and memory costs. Sparse Mixture-of-Experts (MoEs) offer a promising alternative by activating only a subset…

Computation and Language · Computer Science 2026-04-09 Zeliang Zhang , Nikhil Ghosh , Jiani Liu , Bin Yu , Xiaodong Liu

Despite the remarkable performance, modern deep neural networks are inevitably accompanied by a significant amount of computational cost for learning and deployment, which may be incompatible with their usage on edge devices. Recent efforts…

Computer Vision and Pattern Recognition · Computer Science 2022-03-11 Seul-Ki Yeom , Kyung-Hwan Shim , Jee-Hyun Hwang

Despite the popularization of deep neural networks (DNNs) in many fields, it is still challenging to deploy state-of-the-art models to resource-constrained devices due to high computational overhead. Model pruning provides a feasible…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Hui Tang , Yao Lu , Qi Xuan

Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently…

Neural and Evolutionary Computing · Computer Science 2019-05-28 Xiaoliang Dai , Hongxu Yin , Niraj K. Jha

We propose a novel Two-Stage framework for Structured Pruning (\textsc{2SSP}) for pruning Large Language Models (LLMs), which combines two different strategies of pruning, namely Width and Depth Pruning. The first stage (Width Pruning)…

Computation and Language · Computer Science 2025-08-19 Fabrizio Sandri , Elia Cunegatti , Giovanni Iacca

We introduce Probe Pruning (PP), a novel framework for online, dynamic, structured pruning of Large Language Models (LLMs) applied in a batch-wise manner. PP leverages the insight that not all samples and tokens contribute equally to the…

Computation and Language · Computer Science 2025-02-24 Qi Le , Enmao Diao , Ziyan Wang , Xinran Wang , Jie Ding , Li Yang , Ali Anwar

Network pruning is widely used to compress Deep Neural Networks (DNNs). The Soft Filter Pruning (SFP) method zeroizes the pruned filters during training while updating them in the next training epoch. Thus the trained information of the…

Computer Vision and Pattern Recognition · Computer Science 2020-10-20 Linhang Cai , Zhulin An , Chuanguang Yang , Yongjun Xu

Tree ensembles are machine learning models with strong predictive performance and interpretability, and remain widely used for tabular data. Standard pruning methods for tree ensembles typically optimize an accuracy-compression trade-off…

Machine Learning · Computer Science 2026-05-28 Haruki Yajima , Yusuke Matsui

A typical deep neural network (DNN) has a large number of trainable parameters. Choosing a network with proper capacity is challenging and generally a larger network with excessive capacity is trained. Pruning is an established approach to…

Neural and Evolutionary Computing · Computer Science 2021-03-01 Hojjat Salehinejad , Shahrokh Valaee