中文
相关论文

相关论文: HALO: Learning to Prune Neural Networks with Shrin…

200 篇论文

Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of…

人工智能 · 计算机科学 2023-07-03 Peng Mi , Li Shen , Tianhe Ren , Yiyi Zhou , Tianshuo Xu , Xiaoshuai Sun , Tongliang Liu , Rongrong Ji , Dacheng Tao

Sparsity in the structure of Neural Networks can lead to less energy consumption, less memory usage, faster computation times on convenient hardware, and automated machine learning. If sparsity gives rise to certain kinds of structure, it…

机器学习 · 计算机科学 2021-07-28 Julian Stier , Harshil Darji , Michael Granitzer

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…

神经与进化计算 · 计算机科学 2023-09-25 Hugo Tessier , Ghouti Boukli Hacene , Vincent Gripon

Acoustic Scene Classification (ASC) algorithms are usually expected to be deployed in resource-constrained systems. Existing works reduce the complexity of ASC algorithms by pruning some components, e.g. pruning channels in neural network.…

声音 · 计算机科学 2023-07-21 Yiqiang Cai , Shengchen Li

Deep neural networks with lots of parameters are typically used for large-scale computer vision tasks such as image classification. This is a result of using dense matrix multiplications and convolutions. However, sparse computations are…

计算机视觉与模式识别 · 计算机科学 2016-11-22 Suraj Srinivas , Akshayvarun Subramanya , R. Venkatesh Babu

Neural network pruning is a highly effective technique aimed at reducing the computational and memory demands of large neural networks. In this research paper, we present a novel approach to pruning neural networks utilizing Bayesian…

机器学习 · 统计学 2023-08-07 Sunil Mathew , Daniel B. Rowe

Sparse modeling is a powerful framework for data analysis and processing. Traditionally, encoding in this framework is done by solving an l_1-regularized linear regression problem, usually called Lasso. In this work we first combine the…

信息论 · 计算机科学 2010-03-02 Pablo Sprechmann , Ignacio Ramirez , Guillermo Sapiro , Yonina C. Eldar

Deep neural networks (DNNs) are used in many applications, but their large size and high computational cost make them hard to run on devices with limited resources. Two widely used techniques to address this challenge are weight…

计算机视觉与模式识别 · 计算机科学 2025-11-12 Dan Liu , Nikita Dvornik , Xue Liu

Neural models for NLP typically use large numbers of parameters to reach state-of-the-art performance, which can lead to excessive memory usage and increased runtime. We present a structure learning method for learning sparse,…

计算与语言 · 计算机科学 2019-09-09 Jesse Dodge , Roy Schwartz , Hao Peng , Noah A. Smith

Sparse deep neural networks have proven to be efficient for predictive model building in large-scale studies. Although several works have studied theoretical and numerical properties of sparse neural architectures, they have primarily…

机器学习 · 统计学 2023-09-18 Sanket Jantre , Shrijita Bhattacharya , Tapabrata Maiti

Many applications require sparse neural networks due to space or inference time restrictions. There is a large body of work on training dense networks to yield sparse networks for inference, but this limits the size of the largest trainable…

机器学习 · 计算机科学 2021-07-26 Utku Evci , Trevor Gale , Jacob Menick , Pablo Samuel Castro , Erich Elsen

Pruning large neural networks while maintaining their performance is often desirable due to the reduced space and time complexity. In existing methods, pruning is done within an iterative optimization procedure with either heuristically…

计算机视觉与模式识别 · 计算机科学 2019-02-26 Namhoon Lee , Thalaiyasingam Ajanthan , Philip H. S. Torr

"Sparse" neural networks, in which relatively few neurons or connections are active, are common in both machine learning and neuroscience. Whereas in machine learning, "sparsity" is related to a penalty term that leads to some connecting…

神经与进化计算 · 计算机科学 2021-08-19 Luca Manneschi , Andrew C. Lin , Eleni Vasilaki

Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where…

机器学习 · 统计学 2017-11-07 Christos Louizos , Karen Ullrich , Max Welling

The success of DNN pruning has led to the development of energy-efficient inference accelerators that support pruned models with sparse weight and activation tensors. Because the memory layouts and dataflows in these architectures are…

神经与进化计算 · 计算机科学 2020-09-24 Dingqing Yang , Amin Ghasemazar , Xiaowei Ren , Maximilian Golub , Guy Lemieux , Mieszko Lis

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…

机器学习 · 计算机科学 2021-03-26 Deniz Gurevin , Shanglin Zhou , Lynn Pepin , Bingbing Li , Mikhail Bragin , Caiwen Ding , Fei Miao

We propose a reconfigurable hardware architecture for deep neural networks (DNNs) capable of online training and inference, which uses algorithmically pre-determined, structured sparsity to significantly lower memory and computational…

神经与进化计算 · 计算机科学 2017-11-07 Sourya Dey , Yinan Shao , Keith M. Chugg , Peter A. Beerel

The deployment of Deep Neural Networks (DNNs) on edge devices is hindered by the substantial gap between performance requirements and available processing power. While recent research has made significant strides in developing pruning…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Hamid Mousavi , Mohammad Loni , Mina Alibeigi , Masoud Daneshtalab

Deep Neural Networks have achieved extraordinary results on image classification tasks, but have been shown to be vulnerable to attacks with carefully crafted perturbations of the input data. Although most attacks usually change values of…

计算机视觉与模式识别 · 计算机科学 2019-05-28 Apostolos Modas , Seyed-Mohsen Moosavi-Dezfooli , Pascal Frossard

We add a set of convex constraints to the lasso to produce sparse interaction models that honor the hierarchy restriction that an interaction only be included in a model if one or both variables are marginally important. We give a precise…

统计方法学 · 统计学 2013-06-20 Jacob Bien , Jonathan Taylor , Robert Tibshirani