English
Related papers

Related papers: An Empirical Model of Large-Batch Training

200 papers

Understanding when the noise in stochastic gradient descent (SGD) affects generalization of deep neural networks remains a challenge, complicated by the fact that networks can operate in distinct training regimes. Here we study how the…

Machine Learning · Computer Science 2023-05-31 Antonio Sclocchi , Mario Geiger , Matthieu Wyart

Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adversarial robustness across 36 state-of-the-art vision models…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Marco Zimmerli , Andreas Plesner , Till Aczel , Roger Wattenhofer

Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize…

Machine Learning · Computer Science 2021-05-19 Mattia Segu , Alessio Tonioni , Federico Tombari

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

In deep learning, mini-batch training is commonly used to optimize network parameters. However, the traditional mini-batch method may not learn the under-represented samples and complex patterns in the data, leading to a longer time for…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Subin Sahayam , John Zakkam , Umarani Jayaraman

We formulate a general framework for competitive gradient-based learning that encompasses a wide breadth of multi-agent learning algorithms, and analyze the limiting behavior of competitive gradient-based learning algorithms using dynamical…

Machine Learning · Computer Science 2020-02-21 Eric Mazumdar , Lillian J. Ratliff , S. Shankar Sastry

It is common practice to decay the learning rate. Here we show one can usually obtain the same learning curve on both training and test sets by instead increasing the batch size during training. This procedure is successful for stochastic…

Machine Learning · Computer Science 2018-02-27 Samuel L. Smith , Pieter-Jan Kindermans , Chris Ying , Quoc V. Le

With an increasing demand for training powers for deep learning algorithms and the rapid growth of computation resources in data centers, it is desirable to dynamically schedule different distributed deep learning tasks to maximize resource…

Machine Learning · Computer Science 2019-05-03 Haibin Lin , Hang Zhang , Yifei Ma , Tong He , Zhi Zhang , Sheng Zha , Mu Li

Scaling issues are mundane yet irritating for practitioners of reinforcement learning. Error scales vary across domains, tasks, and stages of learning; sometimes by many orders of magnitude. This can be detrimental to learning speed and…

Machine Learning · Computer Science 2021-05-13 Tom Schaul , Georg Ostrovski , Iurii Kemaev , Diana Borsa

Training deep neural networks using a large batch size has shown promising results and benefits many real-world applications. However, the optimizer converges slowly at early epochs and there is a gap between large-batch deep learning…

Machine Learning · Computer Science 2020-02-06 Zhouyuan Huo , Bin Gu , Heng Huang

Modern computer vision algorithms often rely on very large training datasets. However, it is conceivable that a carefully selected subsample of the dataset is sufficient for training. In this paper, we propose a gradient-based importance…

Machine Learning · Computer Science 2018-12-03 Kailas Vodrahalli , Ke Li , Jitendra Malik

Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection. Training with smaller resolutions enables faster training at the expense of a drop in accuracy. Conversely,…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Elvis Nunez , Thomas Merth , Anish Prabhu , Mehrdad Farajtabar , Mohammad Rastegari , Sachin Mehta , Maxwell Horton

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

Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…

Computer Vision and Pattern Recognition · Computer Science 2023-02-13 Peng Cui , Yang Yue , Zhijie Deng , Jun Zhu

Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter updates required to achieve low training error. However, it…

Machine Learning · Computer Science 2019-05-31 Angus Galloway , Anna Golubeva , Thomas Tanay , Medhat Moussa , Graham W. Taylor

How diffusion models generalize beyond their training set is not known, and is somewhat mysterious given two facts: the optimum of the denoising score matching (DSM) objective usually used to train diffusion models is the score function of…

Machine Learning · Computer Science 2025-04-18 John J. Vastola

We study the compute-optimal trade-off between model and training data set sizes for large neural networks. Our result suggests a linear relation similar to that supported by the empirical analysis of chinchilla. While that work studies…

Machine Learning · Computer Science 2023-10-20 Hong Jun Jeon , Benjamin Van Roy

In multi-domain learning, a single model is trained on diverse data domains to leverage shared knowledge and improve generalization. The order in which the data from these domains is used for training can significantly affect the model's…

Machine Learning · Computer Science 2025-01-28 Alexey Rukhovich , Alexander Podolskiy , Irina Piontkovskaya

The width of a neural network matters since increasing the width will necessarily increase the model capacity. However, the performance of a network does not improve linearly with the width and soon gets saturated. In this case, we argue…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Shuai Zhao , Liguang Zhou , Wenxiao Wang , Deng Cai , Tin Lun Lam , Yangsheng Xu

Batch Normalization (BN) is an important preprocessing step to many deep learning applications. Since it is a data-dependent process, for some homogeneous datasets it is a redundant or even a performance-degrading process. In this paper, we…

Machine Learning · Computer Science 2022-12-01 Wael Alsobhi , Tarik Alafif , Alaa Abdel-Hakim , Weiwei Zong