English
Related papers

Related papers: On the Training Instability of Shuffling SGD with …

200 papers

Random reshuffling with momentum (RRM) corresponds to the SGD optimizer with momentum option enabled, as found in many machine learning libraries like PyTorch and TensorFlow. Despite its widespread use, the convergence properties of RRM do…

Optimization and Control · Mathematics 2026-03-24 Junwen Qiu , Bohao Ma , Andre Milzarek

Machine learning models, meticulously optimized for source data, often fail to predict target data when faced with distribution shifts (DSs). Previous benchmarking studies, though extensive, have mainly focused on simple DSs. Recognizing…

Machine Learning · Computer Science 2025-01-09 Myeongho Jeon , Suhwan Choi , Hyoje Lee , Teresa Yeo

Understanding the algorithmic bias of \emph{stochastic gradient descent} (SGD) is one of the key challenges in modern machine learning and deep learning theory. Most of the existing works, however, focus on \emph{very small or even…

Machine Learning · Computer Science 2021-03-30 Jingfeng Wu , Difan Zou , Vladimir Braverman , Quanquan Gu

Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness,…

Machine Learning · Computer Science 2016-02-29 Thomas Hofmann , Aurelien Lucchi , Simon Lacoste-Julien , Brian McWilliams

Traditional normalization techniques (e.g., Batch Normalization and Instance Normalization) generally and simplistically assume that training and test data follow the same distribution. As distribution shifts are inevitable in real-world…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Zhiqiang Tang , Yunhe Gao , Yi Zhu , Zhi Zhang , Mu Li , Dimitris Metaxas

In computer vision and natural language processing, innovations in model architecture that increase model capacity have reliably translated into gains in performance. In stark contrast with this trend, state-of-the-art reinforcement…

Machine Learning · Computer Science 2022-01-05 Johan Bjorck , Carla P. Gomes , Kilian Q. Weinberger

In this paper, we consider distributed optimization problems where $n$ agents, each possessing a local cost function, collaboratively minimize the average of the local cost functions over a connected network. To solve the problem, we…

Optimization and Control · Mathematics 2023-03-24 Kun Huang , Xiao Li , Andre Milzarek , Shi Pu , Junwen Qiu

In large-scale time series forecasting, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset. In this paper, we provably show under such…

Machine Learning · Computer Science 2021-06-14 Yucheng Lu , Youngsuk Park , Lifan Chen , Yuyang Wang , Christopher De Sa , Dean Foster

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

Despite transformers being considered as the new standard in computer vision, convolutional neural networks (CNNs) still outperform them in low-data regimes. Nonetheless, CNNs often make decisions based on narrow, specific regions of input…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 David Bertoin , Eduardo Hugo Sanchez , Mehdi Zouitine , Emmanuel Rachelson

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some…

Computation and Language · Computer Science 2018-11-05 Deren Lei , Zichen Sun , Yijun Xiao , William Yang Wang

It has long been argued that minibatch stochastic gradient descent can generalize better than large batch gradient descent in deep neural networks. However recent papers have questioned this claim, arguing that this effect is simply a…

Machine Learning · Computer Science 2020-06-29 Samuel L. Smith , Erich Elsen , Soham De

Modern deep neural network (DNN) trainings utilize various training techniques, e.g., nonlinear activation functions, batch normalization, skip-connections, etc. Despite their effectiveness, it is still mysterious how they help accelerate…

Machine Learning · Computer Science 2024-03-05 Cheng Chen , Junjie Yang , Yi Zhou

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

Deep neural networks rely heavily on normalization methods to improve their performance and learning behavior. Although normalization methods spurred the development of increasingly deep and efficient architectures, they also increase the…

Machine Learning · Computer Science 2021-10-06 Alexander Fuchs , Christian Knoll , Franz Pernkopf

Is Stochastic Gradient Descent (SGD) substantially different from Metropolis Monte Carlo dynamics? This is a fundamental question at the time of understanding the most used training algorithm in the field of Machine Learning, but it…

Disordered Systems and Neural Networks · Physics 2024-05-31 Maria Chiara Angelini , Angelo Giorgio Cavaliere , Raffaele Marino , Federico Ricci-Tersenghi

Intriguing empirical evidence exists that deep learning can work well with exoticschedules for varying the learning rate. This paper suggests that the phenomenon may be due to Batch Normalization or BN, which is ubiquitous and provides…

Machine Learning · Computer Science 2019-11-22 Zhiyuan Li , Sanjeev Arora

As a crucial scheme to accelerate the deep neural network (DNN) training, distributed stochastic gradient descent (DSGD) is widely adopted in many real-world applications. In most distributed deep learning (DL) frameworks, DSGD is…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-07-17 Xiang Yang

The mini-batch stochastic gradient descent (SGD) algorithm is widely used in training machine learning models, in particular deep learning models. We study SGD dynamics under linear regression and two-layer linear networks, with an easy…

Optimization and Control · Mathematics 2020-04-29 Xin Qian , Diego Klabjan

Multi-epoch, small-batch, Stochastic Gradient Descent (SGD) has been the method of choice for learning with large over-parameterized models. A popular theory for explaining why SGD works well in practice is that the algorithm has an…

Machine Learning · Computer Science 2021-07-13 Satyen Kale , Ayush Sekhari , Karthik Sridharan