English
Related papers

Related papers: Revisiting Small Batch Training for Deep Neural Ne…

200 papers

This work presents a novel training technique for deep neural networks that makes use of additional data from a distribution that is different from that of the original input data. This technique aims to reduce overfitting and improve the…

Computer Vision and Pattern Recognition · Computer Science 2020-06-09 Pravendra Singh , Pratik Mazumder , Vinay P. Namboodiri

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for…

Machine Learning · Computer Science 2019-03-05 Jasmine Collins , Johannes Balle , Jonathon Shlens

Stochastic gradient descent with a large initial learning rate is widely used for training modern neural net architectures. Although a small initial learning rate allows for faster training and better test performance initially, the large…

Machine Learning · Computer Science 2020-04-28 Yuanzhi Li , Colin Wei , Tengyu Ma

The choice of batch-size in a stochastic optimization algorithm plays a substantial role for both optimization and generalization. Increasing the batch-size used typically improves optimization but degrades generalization. To address the…

Machine Learning · Computer Science 2020-03-03 Yeming Wen , Kevin Luk , Maxime Gazeau , Guodong Zhang , Harris Chan , Jimmy Ba

Neural networks have been proven to be both highly effective within computer vision, and highly vulnerable to adversarial attacks. Consequently, as the use of neural networks increases due to their unrivaled performance, so too does the…

Machine Learning · Computer Science 2023-04-03 Timothy Redgrave , Colton Crum

DNN training is time-consuming and requires efficient multi-accelerator parallelization, where a single training iteration is split over available accelerators. Current approaches often parallelize training using intra-batch…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-24 Ankita Dutta , Nabendu Chaki , Rajat K. De

Neural Networks are function approximators that have achieved state-of-the-art accuracy in numerous machine learning tasks. In spite of their great success in terms of accuracy, their large training time makes it difficult to use them for…

Machine Learning · Computer Science 2017-04-18 Abhishek Sinha , Mausoom Sarkar , Aahitagni Mukherjee , Balaji Krishnamurthy

Scale of data and scale of computation infrastructures together enable the current deep learning renaissance. However, training large-scale deep architectures demands both algorithmic improvement and careful system configuration. In this…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-09-21 Shang-Xuan Zou , Chun-Yen Chen , Jui-Lin Wu , Chun-Nan Chou , Chia-Chin Tsao , Kuan-Chieh Tung , Ting-Wei Lin , Cheng-Lung Sung , Edward Y. Chang

As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer. However,…

Computer Vision and Pattern Recognition · Computer Science 2018-03-01 Guangrun Wang , Jiefeng Peng , Ping Luo , Xinjiang Wang , Liang Lin

Training with larger mini-batches improves the convergence rate and can yield superior performance. However, training with large mini-batches becomes prohibitive for Large Language Models (LLMs), due to the large GPU memory requirement. To…

Machine Learning · Computer Science 2025-05-29 Dang Nguyen , Wenhan Yang , Rathul Anand , Yu Yang , Baharan Mirzasoleiman

The choice of initial learning rate can have a profound effect on the performance of deep networks. We present a class of neural networks with solvable training dynamics, and confirm their predictions empirically in practical deep learning…

Machine Learning · Statistics 2020-03-05 Aitor Lewkowycz , Yasaman Bahri , Ethan Dyer , Jascha Sohl-Dickstein , Guy Gur-Ari

Ensembles, where multiple neural networks are trained individually and their predictions are averaged, have been shown to be widely successful for improving both the accuracy and predictive uncertainty of single neural networks. However, an…

Machine Learning · Computer Science 2020-02-21 Yeming Wen , Dustin Tran , Jimmy Ba

Micro-batch clipping, a gradient clipping method, has recently shown potential in enhancing auto-speech recognition (ASR) model performance. However, the underlying mechanism behind this improvement remains mysterious, particularly the…

Machine Learning · Computer Science 2024-08-30 Lun Wang

We develop an approach to efficiently grow neural networks, within which parameterization and optimization strategies are designed by considering their effects on the training dynamics. Unlike existing growing methods, which follow simple…

Machine Learning · Computer Science 2023-06-23 Xin Yuan , Pedro Savarese , Michael Maire

The choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on accelerating convergence and reducing the effects of the…

Computation and Language · Computer Science 2020-05-06 Hongfei Xu , Josef van Genabith , Deyi Xiong , Qiuhui Liu

Deep Neural Networks (DNN) have achieved human level performance in many image analytics tasks but DNNs are mostly deployed to GPU platforms that consume a considerable amount of power. Brain-inspired spiking neuromorphic chips consume low…

Neural and Evolutionary Computing · Computer Science 2016-05-26 Antonio Jimeno Yepes , Jianbin Tang

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

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

Machine Learning · Computer Science 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

Spiking neural networks (SNNs) are a promising candidate for biologically-inspired and energy efficient computation. However, their simulation is notoriously time consuming, and may be seen as a bottleneck in developing competitive training…

Neural and Evolutionary Computing · Computer Science 2019-09-06 Daniel J. Saunders , Cooper Sigrist , Kenneth Chaney , Robert Kozma , Hava T. Siegelmann

Standard convolutional neural networks(CNNs) require consistent image resolutions in both training and testing phase. However, in practice, testing with smaller image sizes is necessary for fast inference. We show that trivially evaluating…

Computer Vision and Pattern Recognition · Computer Science 2020-09-08 Zhuoran Yu , Aojun Zhou , Yukun Ma , Yudian Li , Xiaohan Zhang , Ping Luo