English
Related papers

Related papers: Smooth Model Compression without Fine-Tuning

200 papers

Deep reinforcement learning (DRL) has shown remarkable success in complex autonomous driving scenarios. However, DRL models inevitably bring high memory consumption and computation, which hinders their wide deployment in resource-limited…

Machine Learning · Computer Science 2024-02-09 Wensheng Su , Zhenni Li , Minrui Xu , Jiawen Kang , Dusit Niyato , Shengli Xie

Existing high-performance deep learning models require very intensive computing. For this reason, it is difficult to embed a deep learning model into a system with limited resources. In this paper, we propose the novel idea of the network…

Machine Learning · Computer Science 2019-02-13 Dae-Woong Jeong , Jaehun Kim , Youngseok Kim , Tae-Ho Kim , Myungsu Chae

In recent years, deep neural networks have achieved great success in the field of computer vision. However, it is still a big challenge to deploy these deep models on resource-constrained embedded devices such as mobile robots, smart phones…

Computer Vision and Pattern Recognition · Computer Science 2018-05-30 Yiming Hu , Siyang Sun , Jianquan Li , Xingang Wang , Qingyi Gu

This work focuses on reducing neural network size, which is a major driver of neural network execution time, power consumption, bandwidth, and memory footprint. A key challenge is to reduce size in a manner that can be exploited readily for…

Machine Learning · Computer Science 2025-06-18 Szabolcs Cséfalvay , James Imber

Despite the superior performance, it is challenging to deploy foundation models or large language models (LLMs) due to their massive parameters and computations. While pruning is a promising technique to reduce model size and accelerate the…

Machine Learning · Computer Science 2024-10-22 Pu Zhao , Fei Sun , Xuan Shen , Pinrui Yu , Zhenglun Kong , Yanzhi Wang , Xue Lin

Model compression has gained significant popularity as a means to alleviate the computational and memory demands of machine learning models. Each compression technique leverages unique features to reduce the size of neural networks.…

Machine Learning · Computer Science 2024-08-20 Yingtao Shen , Minqing Sun , Jianzhe Lin , Jie Zhao , An Zou

We study the neural network (NN) compression problem, viewing the tension between the compression ratio and NN performance through the lens of rate-distortion theory. We choose a distortion metric that reflects the effect of NN compression…

Machine Learning · Computer Science 2022-02-11 Berivan Isik , Tsachy Weissman , Albert No

Neural Network Pruning has been established as driving force in the exploration of memory and energy efficient solutions with high throughput both during training and at test time. In this paper, we introduce a novel criterion for model…

Machine Learning · Computer Science 2025-12-09 Angelos-Christos Maroudis , Sotirios Xydis

Compressing neural networks is a key step when deploying models for real-time or embedded applications. Factorizing the model's matrices using low-rank approximations is a promising method for achieving compression. While it is possible to…

Machine Learning · Computer Science 2023-10-20 Lucas Maison , Hélion du Mas des Bourboux , Thomas Courtat

Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory. Model compression methods address this…

Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a…

Machine Learning · Computer Science 2018-02-06 Jianbo Ye , Xin Lu , Zhe Lin , James Z. Wang

Network pruning is a widely used technique to reduce computation cost and model size for deep neural networks. However, the typical three-stage pipeline, i.e., training, pruning and retraining (fine-tuning) significantly increases the…

Machine Learning · Computer Science 2021-03-26 Deniz Gurevin , Shanglin Zhou , Lynn Pepin , Bingbing Li , Mikhail Bragin , Caiwen Ding , Fei Miao

We present a computationally efficient method for compressing a trained neural network without using real data. We break the problem of data-free network compression into independent layer-wise compressions. We show how to efficiently…

Computer Vision and Pattern Recognition · Computer Science 2022-05-23 Maxwell Horton , Yanzi Jin , Ali Farhadi , Mohammad Rastegari

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

We introduce a DNN training technique that learns only a fraction of the full parameter set without incurring an accuracy penalty. To do this, our algorithm constrains the total number of weights updated during backpropagation to those with…

Machine Learning · Computer Science 2019-11-26 Maximilian Golub , Guy Lemieux , Mieszko Lis

The increasing size and complexity of Large Language Models (LLMs) pose challenges for their deployment on personal computers and mobile devices. Aggressive post-training model compression is necessary to reduce the models' size, but it…

Computation and Language · Computer Science 2024-10-01 Zining Zhang , Yao Chen , Bingsheng He , Zhenjie Zhang

Large neural networks are heavily over-parameterized. This is done because it improves training to optimality. However once the network is trained, this means many parameters can be zeroed, or pruned, leaving an equivalent sparse neural…

Machine Learning · Computer Science 2022-07-12 Michael G. Rawson

Over the last century, deep learning models have become the state-of-the-art for solving complex computer vision problems. These modern computer vision models have millions of parameters, which presents two major challenges: (1) the…

Computer Vision and Pattern Recognition · Computer Science 2025-01-15 Florian Merkle , David Weber , Pascal Schöttle , Stephan Schlögl , Martin Nocker

In the traditional deep compression framework, iteratively performing network pruning and quantization can reduce the model size and computation cost to meet the deployment requirements. However, such a step-wise application of pruning and…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Wenting Tang , Xingxing Wei , Bo Li

Quantization, knowledge distillation, and magnitude pruning are among the most popular methods for neural network compression in NLP. Independently, these methods reduce model size and can accelerate inference, but their relative benefit…

Computation and Language · Computer Science 2022-08-23 Rajiv Movva , Jinhao Lei , Shayne Longpre , Ajay Gupta , Chris DuBois