English
Related papers

Related papers: Dynamically Adjusting Transformer Batch Size by Mo…

200 papers

The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep the distributed processors fully utilized requires…

Machine Learning · Computer Science 2020-01-06 Zhewei Yao , Amir Gholami , Daiyaan Arfeen , Richard Liaw , Joseph Gonzalez , Kurt Keutzer , Michael Mahoney

The impact of gradient noise on training deep models is widely acknowledged but not well understood. In this context, we study the distribution of gradients during training. We introduce a method, Gradient Clustering, to minimize the…

Machine Learning · Computer Science 2020-07-10 Fartash Faghri , David Duvenaud , David J. Fleet , Jimmy Ba

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

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

This paper presents a methodology for selecting the mini-batch size that minimizes Stochastic Gradient Descent (SGD) learning time for single and multiple learner problems. By decoupling algorithmic analysis issues from hardware and…

Machine Learning · Computer Science 2019-11-18 Michael P. Perrone , Haidar Khan , Changhoan Kim , Anastasios Kyrillidis , Jerry Quinn , Valentina Salapura

Gradient methods are widely used in optimization problems. In practice, while the smoothness parameter can be estimated utilizing techniques such as backtracking, estimating the strong convexity parameter remains a challenge; moreover, even…

Optimization and Control · Mathematics 2026-02-17 Xiaozhe Hu , Sara Pollock , Zhongqin Xue , Yunrong Zhu

We theoretically analyzed the convergence behavior of Riemannian stochastic gradient descent (RSGD) and found that using an increasing batch size leads to faster convergence than using a constant batch size, not only with a constant…

Machine Learning · Computer Science 2025-10-14 Kanata Oowada , Hideaki Iiduka

Hyperparameter selection generally relies on running multiple full training trials, with selection based on validation set performance. We propose a gradient-based approach for locally adjusting hyperparameters during training of the model.…

Machine Learning · Computer Science 2016-06-20 Jelena Luketina , Mathias Berglund , Klaus Greff , Tapani Raiko

We investigate the dynamical and convergent properties of stochastic gradient descent (SGD) applied to Deep Neural Networks (DNNs). Characterizing the relation between learning rate, batch size and the properties of the final minima, such…

Machine Learning · Computer Science 2018-09-14 Stanisław Jastrzębski , Zachary Kenton , Devansh Arpit , Nicolas Ballas , Asja Fischer , Yoshua Bengio , Amos Storkey

This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when data is limited. The method builds on a base loss function…

Computation and Language · Computer Science 2025-06-03 Hongye Zheng , Yichen Wang , Ray Pan , Guiran Liu , Binrong Zhu , Hanlu Zhang

The convergence behavior of mini-batch stochastic gradient descent (SGD) is highly sensitive to the batch size and learning rate settings. Recent theoretical studies have identified the existence of a critical batch size that minimizes…

Machine Learning · Computer Science 2025-08-08 Hikaru Umeda , Hideaki Iiduka

Despite exceptional achievements, training neural networks remains computationally expensive and is often plagued by instabilities that can degrade convergence. While learning rate schedules can help mitigate these issues, finding optimal…

Machine Learning · Computer Science 2026-03-30 Benoit Dherin , Benny Avelin , Anders Karlsson , Hanna Mazzawi , Javier Gonzalvo , Michael Munn

Variance-reduced algorithms, although achieve great theoretical performance, can run slowly in practice due to the periodic gradient estimation with a large batch of data. Batch-size adaptation thus arises as a promising approach to…

Optimization and Control · Mathematics 2020-07-28 Kaiyi Ji , Zhe Wang , Bowen Weng , Yi Zhou , Wei Zhang , Yingbin Liang

In machine learning applications, it is well known that carefully designed learning rate (step size) schedules can significantly improve the convergence of commonly used first-order optimization algorithms. Therefore how to set step size…

Optimization and Control · Mathematics 2023-10-19 Xiaoyu Wang , Mikael Johansson , Tong Zhang

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 say an algorithm is batch size-invariant if changes to the batch size can largely be compensated for by changes to other hyperparameters. Stochastic gradient descent is well-known to have this property at small batch sizes, via the…

Machine Learning · Computer Science 2023-03-28 Jacob Hilton , Karl Cobbe , John Schulman

Deep Neural Networks are generally trained using iterative gradient updates. Magnitudes of gradients are affected by many factors, including choice of activation functions and initialization. More importantly, gradient magnitudes can…

Machine Learning · Computer Science 2017-08-25 Sami Abu-El-Haija

This paper presents a novel adaptation of the Stochastic Gradient Descent (SGD), termed AdaBatchGrad. This modification seamlessly integrates an adaptive step size with an adjustable batch size. An increase in batch size and a decrease in…

Machine Learning · Computer Science 2024-02-09 Petr Ostroukhov , Aigerim Zhumabayeva , Chulu Xiang , Alexander Gasnikov , Martin Takáč , Dmitry Kamzolov

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

Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on…