English
Related papers

Related papers: Structural Dropout for Model Width Compression

200 papers

Dropout as regularization has been used extensively to prevent overfitting for training neural networks. During training, units and their connections are randomly dropped, which could be considered as sampling many different submodels from…

Machine Learning · Computer Science 2022-04-28 Zhaoyuan Yang , Arpit Jain

Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices. Although capable of reducing a reasonable amount of model…

Machine Learning · Computer Science 2021-06-17 Sheng Lin , Wei Jiang , Wei Wang , Kaidi Xu , Yanzhi Wang , Shan Liu , Songnan Li

This paper proposes a method to effectively perform joint training-and-pruning based on adaptive dropout layers with unit-wise retention probabilities. The proposed method is based on the estimation of a unit-wise retention probability in a…

Computation and Language · Computer Science 2024-12-09 Yotaro Kubo , Xingyu Cai , Michiel Bacchiani

Large Language Models (LLMs) have achieved significant success across various NLP tasks. However, their massive computational costs limit their widespread use, particularly in real-time applications. Structured pruning offers an effective…

Machine Learning · Computer Science 2025-03-06 Shengkun Tang , Oliver Sieberling , Eldar Kurtic , Zhiqiang Shen , Dan Alistarh

Model compression techniques reduce the computational load and memory consumption of deep neural networks. After the compression operation, e.g. parameter pruning, the model is normally fine-tuned on the original training dataset to recover…

Computer Vision and Pattern Recognition · Computer Science 2023-06-23 Adrian Holzbock , Achyut Hegde , Klaus Dietmayer , Vasileios Belagiannis

Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes…

Machine Learning · Computer Science 2018-12-11 Rohit Keshari , Richa Singh , Mayank Vatsa

Large language models (LLMs) have achieved significant progress across various domains, but their increasing scale results in high computational and memory costs. Recent studies have revealed that LLMs exhibit sparsity, providing the…

Machine Learning · Computer Science 2025-07-01 Mingkuan Feng , Jinyang Wu , Shuai Zhang , Pengpeng Shao , Ruihan Jin , Zhengqi Wen , Jianhua Tao , Feihu Che

Large language models (LLMs) have revolutionized natural language processing, yet their substantial model sizes often require substantial computational resources. To preserve computing resources and accelerate inference speed, it is crucial…

Computation and Language · Computer Science 2025-06-04 Yirao Zhao , Guizhen Chen , Kenji Kawaguchi , Lidong Bing , Wenxuan Zhang

The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. As a result, computation and memory costs in resource-limited applications may be significantly reduced by dropping…

Machine Learning · Statistics 2022-11-10 Wenjing Yang , Ganghua Wang , Jie Ding , Yuhong Yang

Compression and generalization are fundamentally related through Solomonoff induction and the minimum description length principle (MDL), which predict that simpler models generalize better when data arises from low-complexity…

Machine Learning · Computer Science 2026-05-14 Lukas Silvester Barth , Paulo von Petersenn

With the general trend of increasing Convolutional Neural Network (CNN) model sizes, model compression and acceleration techniques have become critical for the deployment of these models on edge devices. In this paper, we provide a…

Machine Learning · Computer Science 2020-05-12 Jiayi Liu , Samarth Tripathi , Unmesh Kurup , Mohak Shah

This paper presents a novel method which simultaneously learns the number of filters and network features repeatedly over multiple epochs. We propose a novel pruning loss to explicitly enforces the optimizer to focus on promising candidate…

Computer Vision and Pattern Recognition · Computer Science 2019-06-12 Tinghuai Wang , Lixin Fan , Huiling Wang

Convolutional neural network (CNN) pruning has become one of the most successful network compression approaches in recent years. Existing works on network pruning usually focus on removing the least important filters in the network to…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Zi Wang , Chengcheng Li , Xiangyang Wang

Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks, including language modeling, understanding, and generation. However, the increased memory and computational costs associated with…

Computation and Language · Computer Science 2024-11-05 Shangqian Gao , Chi-Heng Lin , Ting Hua , Tang Zheng , Yilin Shen , Hongxia Jin , Yen-Chang Hsu

Dropout is a widely used regularization technique in deep learning, but its effects are typically realized through stochastic masking rather than explicit optimization objectives. We propose a deterministic formulation that expresses…

Machine Learning · Computer Science 2026-04-23 Vidhi Agrawal , Illia Oleksiienko , Alexandros Iosifidis

Machine Learning models should ideally be compact and robust. Compactness provides efficiency and comprehensibility whereas robustness provides resilience. Both topics have been studied in recent years but in isolation. Here we present a…

Machine Learning · Computer Science 2021-03-16 Omri Armstrong , Ran Gilad-Bachrach

Model Compression has drawn much attention within the deep learning community recently. Compressing a dense neural network offers many advantages including lower computation cost, deployability to devices of limited storage and memories,…

Machine Learning · Computer Science 2024-11-04 Diptarka Saha , Zihe Liu , Feng Liang

Pruning - that is, setting a significant subset of the parameters of a neural network to zero - is one of the most popular methods of model compression. Yet, several recent works have raised the issue that pruning may induce or exacerbate…

Computer Vision and Pattern Recognition · Computer Science 2023-04-26 Eugenia Iofinova , Alexandra Peste , Dan Alistarh

Model compression is a critical area of research in deep learning, in particular in vision, driven by the need to lighten models memory or computational footprints. While numerous methods for model compression have been proposed, most focus…

Machine Learning · Computer Science 2025-04-08 Jeremy Morlier , Mathieu Leonardon , Vincent Gripon

Pruning is a compression method which aims to improve the efficiency of neural networks by reducing their number of parameters while maintaining a good performance, thus enhancing the performance-to-cost ratio in nontrivial ways. Of…

Neural and Evolutionary Computing · Computer Science 2023-09-25 Hugo Tessier , Ghouti Boukli Hacene , Vincent Gripon
‹ Prev 1 4 5 6 7 8 10 Next ›