English
Related papers

Related papers: Adam Induces Implicit Weight Sparsity in Rectifier…

200 papers

This study investigates how weight decay affects the update behavior of individual neurons in deep neural networks through a combination of applied analysis and experimentation. Weight decay can cause the expected magnitude and angular…

Machine Learning · Computer Science 2024-06-04 Atli Kosson , Bettina Messmer , Martin Jaggi

Deep neural networks (DNNs) have brought significant advancements in various applications in recent years, such as image recognition, speech recognition, and natural language processing. In particular, Vision Transformers (ViTs) have…

Machine Learning · Computer Science 2025-03-07 Leonid Berlyand , Theo Bourdais , Houman Owhadi , Yitzchak Shmalo

To fully uncover the great potential of deep neural networks (DNNs), various learning algorithms have been developed to improve the model's generalization ability. Recently, sharpness-aware minimization (SAM) establishes a generic scheme…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Tao Li , Weihao Yan , Zehao Lei , Yingwen Wu , Kun Fang , Ming Yang , Xiaolin Huang

The parameters of a neural network are naturally organized in groups, some of which might not contribute to its overall performance. To prune out unimportant groups of parameters, we can include some non-differentiable penalty to the…

Machine Learning · Computer Science 2023-01-06 Tristan Deleu , Yoshua Bengio

The demand for efficient processing of deep neural networks (DNNs) on embedded devices is a significant challenge limiting their deployment. Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Matteo Grimaldi , Darshan C. Ganji , Ivan Lazarevich , Sudhakar Sah

Network pruning is aimed at imposing sparsity in a neural network architecture by increasing the portion of zero-valued weights for reducing its size regarding energy-efficiency consideration and increasing evaluation speed. In most of the…

Machine Learning · Computer Science 2018-07-17 Amirsina Torfi , Rouzbeh A. Shirvani , Sobhan Soleymani , Nasser M. Nasrabadi

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed that compared with (stochastic) gradient descent, Adam can converge to a different solution with a…

Machine Learning · Computer Science 2021-08-26 Difan Zou , Yuan Cao , Yuanzhi Li , Quanquan Gu

Interpretable machine learning has demonstrated impressive performance while preserving explainability. In particular, neural additive models (NAM) offer the interpretability to the black-box deep learning and achieve state-of-the-art…

Machine Learning · Statistics 2022-02-28 Shiyun Xu , Zhiqi Bu , Pratik Chaudhari , Ian J. Barnett

Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Yifan Gong , Zheng Zhan , Yanyu Li , Yerlan Idelbayev , Andrey Zharkov , Kfir Aberman , Sergey Tulyakov , Yanzhi Wang , Jian Ren

We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backward pass is performed…

Computer Vision and Pattern Recognition · Computer Science 2020-05-26 Yoojin Choi , Mostafa El-Khamy , Jungwon Lee

In this work, we present some applications of random matrix theory for the training of deep neural networks. Recently, random matrix theory (RMT) has been applied to the overfitting problem in deep learning. Specifically, it has been shown…

Machine Learning · Computer Science 2023-03-17 Yitzchak Shmalo , Jonathan Jenkins , Oleksii Krupchytskyi

We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands…

Machine Learning · Computer Science 2019-02-27 Trevor Gale , Erich Elsen , Sara Hooker

Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them from being deployed to many edge and internet-of-things (IoT)…

Neural and Evolutionary Computing · Computer Science 2021-12-22 Minghai Qin , Tianyun Zhang , Fei Sun , Yen-Kuang Chen , Makan Fardad , Yanzhi Wang , Yuan Xie

We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay.…

Machine Learning · Computer Science 2019-05-14 Dushyant Mehta , Kwang In Kim , Christian Theobalt

We introduce and analyze a new technique for model reduction for deep neural networks. While large networks are theoretically capable of learning arbitrarily complex models, overfitting and model redundancy negatively affects the prediction…

Machine Learning · Computer Science 2017-11-27 Alireza Aghasi , Afshin Abdi , Nam Nguyen , Justin Romberg

Deep neural networks have become very popular in modeling complex nonlinear processes due to their extraordinary ability to fit arbitrary nonlinear functions from data with minimal expert intervention. However, they are almost always…

Chemical Physics · Physics 2023-01-16 Erlend Torje Berg Lundby , Adil Rasheed , Ivar Johan Halvorsen , Jan Tommy Gravdahl

Artificial neural networks (ANNs) may not be worth their computational/memory costs when used in mobile phones or embedded devices. Parameter-pruning algorithms combat these costs, with some algorithms capable of removing over 90% of an…

Machine Learning · Statistics 2018-05-08 Brian Bartoldson , Adrian Barbu , Gordon Erlebacher

Deep Neural Networks (DNNs) are computationally and memory intensive, which makes their hardware implementation a challenging task especially for resource constrained devices such as IoT nodes. To address this challenge, this paper…

Computer Vision and Pattern Recognition · Computer Science 2021-05-10 Mohammed F. Tolba , Huruy Tekle Tesfai , Hani Saleh , Baker Mohammad , Mahmoud Al-Qutayri

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

Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures…

Machine Learning · Computer Science 2018-06-19 Utku Evci