English
Related papers

Related papers: Unlocking optimal batch size schedules using conti…

200 papers

We study how the batch size affects the total gradient variance in differentially private stochastic gradient descent (DP-SGD), seeking a theoretical explanation for the usefulness of large batch sizes. As DP-SGD is the basis of modern DP…

Machine Learning · Statistics 2024-09-20 Ossi Räisä , Joonas Jälkö , Antti Honkela

Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are usually used with a constant batch size chosen by simple…

Machine Learning · Computer Science 2017-06-29 Lukas Balles , Javier Romero , Philipp Hennig

Stochastic Gradient Descent (SGD) methods are prominent for training machine learning and deep learning models. The performance of these techniques depends on their hyperparameter tuning over time and varies for different models and…

Machine Learning · Statistics 2019-08-22 Tomer Lancewicki , Selcuk Kopru

Stochastic gradient descent (SGD) with mini-batching is a standard tool in large-scale optimization, yet its theoretical properties under heavy-tailed gradient noise remain largely unexplored. In this paper we study SGD with increasing…

Probability · Mathematics 2026-05-11 Bartosz Glowacki , Rafal Kulik , Philippe Soulier

We present an optimizer which uses Bayesian optimization to tune the system parameters of distributed stochastic gradient descent (SGD). Given a specific context, our goal is to quickly find efficient configurations which appropriately…

Machine Learning · Statistics 2016-12-04 Valentin Dalibard , Michael Schaarschmidt , Eiko Yoneki

Increasing the mini-batch size for stochastic gradient descent offers significant opportunities to reduce wall-clock training time, but there are a variety of theoretical and systems challenges that impede the widespread success of this…

We propose a first-order stochastic optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. The adaptive regularization is imposed by stochastic process in determining…

Machine Learning · Computer Science 2020-04-15 Kensuke Nakamura , Stefano Soatto , Byung-Woo Hong

We investigate the stochastic gradient descent (SGD) method where the step size lies within a banded region instead of being given by a fixed formula. The optimal convergence rate under mild conditions and large initial step size is proved.…

Optimization and Control · Mathematics 2023-04-10 Xiaoyu Wang , Ya-xiang Yuan

Synchronous strategies with data parallelism, such as the Synchronous StochasticGradient Descent (S-SGD) and the model averaging methods, are widely utilizedin distributed training of Deep Neural Networks (DNNs), largely owing to itseasy…

Machine Learning · Computer Science 2022-11-04 Qing Ye , Yuhao Zhou , Mingjia Shi , Yanan Sun , Jiancheng Lv

Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD). This effectively removes all needs for tuning, while automatically reducing learning rates over time on…

Machine Learning · Computer Science 2013-03-28 Tom Schaul , Yann LeCun

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is…

Machine Learning · Computer Science 2017-02-13 Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , Ping Tak Peter Tang

Stochastic Gradient Descent (SGD) is the key learning algorithm for many machine learning tasks. Because of its computational costs, there is a growing interest in accelerating SGD on HPC resources like GPU clusters. However, the…

Machine Learning · Computer Science 2021-01-20 Peng Jiang , Gagan Agrawal

We investigate how the final parameters found by stochastic gradient descent are influenced by over-parameterization. We generate families of models by increasing the number of channels in a base network, and then perform a large…

Machine Learning · Computer Science 2019-05-10 Daniel S. Park , Jascha Sohl-Dickstein , Quoc V. Le , Samuel L. Smith

We introduce a new, high-throughput, synchronous, distributed, data-parallel, stochastic-gradient-descent learning algorithm. This algorithm uses amortized inference in a compute-cluster-specific, deep, generative, dynamical model to…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-03-14 Michael Teng , Frank Wood

Commonly used optimization algorithms often show a trade-off between good generalization and fast training times. For instance, stochastic gradient descent (SGD) tends to have good generalization; however, adaptive gradient methods have…

Machine Learning · Computer Science 2023-06-14 Aditya Cowsik , Tankut Can , Paolo Glorioso

We analyze the convergence behavior of stochastic gradient descent with momentum (SGDM) under dynamic learning-rate and batch-size schedules by introducing a novel and simpler Lyapunov function. We extend the existing theoretical framework…

Machine Learning · Computer Science 2025-10-13 Yuichi Kondo , Hideaki Iiduka

We showcase important features of the dynamics of the Stochastic Gradient Descent (SGD) in the training of neural networks. We present empirical observations that commonly used large step sizes (i) lead the iterates to jump from one side of…

Machine Learning · Computer Science 2023-06-08 Maksym Andriushchenko , Aditya Varre , Loucas Pillaud-Vivien , Nicolas Flammarion

The performance of stochastic gradient descent (SGD), which is the simplest first-order optimizer for training deep neural networks, depends on not only the learning rate but also the batch size. They both affect the number of iterations…

Machine Learning · Statistics 2024-02-26 Kento Imaizumi , Hideaki Iiduka

Training deep neural networks with Stochastic Gradient Descent, or its variants, requires careful choice of both learning rate and batch size. While smaller batch sizes generally converge in fewer training epochs, larger batch sizes offer…

Machine Learning · Computer Science 2018-02-15 Aditya Devarakonda , Maxim Naumov , Michael Garland

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