English
Related papers

Related papers: SparseOpt: Addressing Normalization-induced Gradie…

200 papers

Pruning the weights of neural networks is an effective and widely-used technique for reducing model size and inference complexity. We develop and test a novel method based on compressed sensing which combines the pruning and training into a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Jonathan W. Siegel , Jianhong Chen , Pengchuan Zhang , Jinchao Xu

Quantization is a technique for reducing deep neural networks (DNNs) training and inference times, which is crucial for training in resource constrained environments or applications where inference is time critical. State-of-the-art (SOTA)…

Machine Learning · Computer Science 2023-05-24 Lorenz Kummer , Kevin Sidak , Tabea Reichmann , Wilfried Gansterer

Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to be sensitive to hyperparameter settings and make…

Machine Learning · Computer Science 2022-11-02 Masud An-Nur Islam Fahim , Jani Boutellier

Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward…

Machine Learning · Computer Science 2022-01-20 An Xu , Zhouyuan Huo , Heng Huang

Training a neural network (NN) typically relies on some type of curve-following method, such as gradient descent (GD) (and stochastic gradient descent (SGD)), ADADELTA, ADAM or limited memory algorithms. Convergence for these algorithms…

Machine Learning · Computer Science 2023-05-08 Michael A Kouritzin , Stephen Styles , Beatrice-Helen Vritsiou

Differentially Private Stochastic Gradient Descent (DP-SGD) limits the amount of private information deep learning models can memorize during training. This is achieved by clipping and adding noise to the model's gradients, and thus…

Computer Vision and Pattern Recognition · Computer Science 2023-06-22 Florian A. Hölzl , Daniel Rueckert , Georgios Kaissis

Several challenges make it difficult for sparse neural networks to compete with dense models. First, setting a large fraction of weights to zero impairs forward and gradient signal propagation. Second, sparse studies often need to test…

Machine Learning · Computer Science 2026-02-04 Nolan Dey , Shane Bergsma , Joel Hestness

Pruning large neural networks to create high-quality, independently trainable sparse masks, which can maintain similar performance to their dense counterparts, is very desirable due to the reduced space and time complexity. As research…

Computer Vision and Pattern Recognition · Computer Science 2022-06-29 Ajay Jaiswal , Haoyu Ma , Tianlong Chen , Ying Ding , Zhangyang Wang

The extensive need for computational resources poses a significant obstacle to deploying large-scale Deep Neural Networks (DNN) on devices with constrained resources. At the same time, studies have demonstrated that a significant number of…

Machine Learning · Computer Science 2024-08-27 Yehonathan Refael , Iftach Arbel , Wasim Huleihel

Data quantization is an effective method to accelerate neural network training and reduce power consumption. However, it is challenging to perform low-bit quantized training: the conventional equal-precision quantization will lead to either…

Machine Learning · Computer Science 2022-11-01 Ruoyang Liu , Chenhan Wei , Yixiong Yang , Wenxun Wang , Huazhong Yang , Yongpan Liu

Deep learning has been the engine powering many successes of data science. However, the deep neural network (DNN), as the basic model of deep learning, is often excessively over-parameterized, causing many difficulties in training,…

Machine Learning · Statistics 2021-03-09 Yan Sun , Qifan Song , Faming Liang

Batch Normalization (BN) has become a core design block of modern Convolutional Neural Networks (CNNs). A typical modern CNN has a large number of BN layers in its lean and deep architecture. BN requires mean and variance calculations over…

Computer Vision and Pattern Recognition · Computer Science 2019-03-04 Wonkyung Jung , Daejin Jung , and Byeongho Kim , Sunjung Lee , Wonjong Rhee , Jung Ho Ahn

Sparse training is emerging as a promising avenue for reducing the computational cost of training neural networks. Several recent studies have proposed pruning methods using learnable thresholds to efficiently explore the non-uniform…

Machine Learning · Computer Science 2023-04-17 Abhisek Kundu , Naveen K. Mellempudi , Dharma Teja Vooturi , Bharat Kaul , Pradeep Dubey

Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to select different…

Computer Vision and Pattern Recognition · Computer Science 2019-03-12 Wenqi Shao , Tianjian Meng , Jingyu Li , Ruimao Zhang , Yudian Li , Xiaogang Wang , Ping Luo

Neoteric works have shown that modern deep learning models can exhibit a sparse double descent phenomenon. Indeed, as the sparsity of the model increases, the test performance first worsens since the model is overfitting the training data;…

Machine Learning · Computer Science 2024-02-09 Victor Quétu , Enzo Tartaglione

Dynamic Sparse Training (DST) is a rapidly evolving area of research that seeks to optimize the sparse initialization of a neural network by adapting its topology during training. It has been shown that under specific conditions, DST is…

Machine Learning · Computer Science 2023-12-01 Aleksandra I. Nowak , Bram Grooten , Decebal Constantin Mocanu , Jacek Tabor

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would…

Computer Vision and Pattern Recognition · Computer Science 2016-06-15 Maya Kabkab , Azadeh Alavi , Rama Chellappa

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

Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks. In contrast to the individually…

Machine Learning · Computer Science 2017-09-19 Sungrae Park , Jun-Keon Park , Su-Jin Shin , Il-Chul Moon