English
Related papers

Related papers: Inefficiency of K-FAC for Large Batch Size Trainin…

200 papers

An important question in deep learning is how higher-order optimization methods affect generalization. In this work, we analyze a stochastic Gauss-Newton (SGN) method with Levenberg-Marquardt damping and mini-batch sampling for training…

Machine Learning · Computer Science 2025-11-13 Semih Cayci

Understanding the convergence performance of asynchronous stochastic gradient descent method (Async-SGD) has received increasing attention in recent years due to their foundational role in machine learning. To date, however, most of the…

Machine Learning · Computer Science 2020-09-02 Xin Zhang , Jia Liu , Zhengyuan Zhu

Stochastic gradient descent with momentum (SGDM), in which a momentum term is added to SGD, has been well studied in both theory and practice. The theoretical studies show that the settings of the learning rate and momentum weight affect…

Machine Learning · Computer Science 2025-09-25 Keisuke Kamo , Hideaki Iiduka

Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While for SGD, doubling the batch size can be equivalent to halving the learning rate, the optimal…

Machine Learning · Computer Science 2025-10-17 Alexandru Meterez , Depen Morwani , Jingfeng Wu , Costin-Andrei Oncescu , Cengiz Pehlevan , Sham Kakade

First-order stochastic methods for solving large-scale non-convex optimization problems are widely used in many big-data applications, e.g. training deep neural networks as well as other complex and potentially non-convex machine learning…

Machine Learning · Computer Science 2020-11-23 Matilde Gargiani , Andrea Zanelli , Quoc Tran-Dinh , Moritz Diehl , Frank Hutter

In this paper, we propose a simple variant of the original stochastic variance reduction gradient (SVRG), where hereafter we refer to as the variance reduced stochastic gradient descent (VR-SGD). Different from the choices of the snapshot…

Machine Learning · Computer Science 2017-04-18 Fanhua Shang

Distributed stochastic gradient descent (SGD) algorithms are widely deployed in training large-scale deep learning models, while the communication overhead among workers becomes the new system bottleneck. Recently proposed gradient…

Machine Learning · Computer Science 2019-11-21 Shaohuai Shi , Xiaowen Chu , Ka Chun Cheung , Simon See

Multi-task learning is useful in NLP because it is often practically desirable to have a single model that works across a range of tasks. In the medical domain, sequential training on tasks may sometimes be the only way to train models,…

Computation and Language · Computer Science 2021-11-12 Denis Jered McInerney , Luyang Kong , Kristjan Arumae , Byron Wallace , Parminder Bhatia

In view of a direct and simple improvement of vanilla SGD, this paper presents a fine-tuning of its step-sizes in the mini-batch case. For doing so, one estimates curvature, based on a local quadratic model and using only noisy gradient…

Machine Learning · Computer Science 2022-02-10 Camille Castera , Jérôme Bolte , Cédric Févotte , Edouard Pauwels

We present a theoretical analysis of stochastic optimization methods in terms of their sensitivity with respect to the step size. We identify a key quantity that, for each method, describes how the performance degrades as the step size…

Optimization and Control · Mathematics 2026-05-27 Fabian Schaipp , Robert M. Gower , Adrien Taylor

Stochastic gradient descent (SGD) for strongly convex functions converges at the rate $\bO(1/k)$. However, achieving good results in practice requires tuning the parameters (for example the learning rate) of the algorithm. In this paper we…

Optimization and Control · Mathematics 2019-07-15 Adam M. Oberman , Mariana Prazeres

We study the effect of mini-batching on the loss landscape of deep neural networks using spiked, field-dependent random matrix theory. We demonstrate that the magnitude of the extremal values of the batch Hessian are larger than those of…

Machine Learning · Statistics 2021-11-08 Diego Granziol , Stefan Zohren , Stephen Roberts

Large batch size training of Neural Networks has been shown to incur accuracy loss when trained with the current methods. The exact underlying reasons for this are still not completely understood. Here, we study large batch size training…

Computer Vision and Pattern Recognition · Computer Science 2021-04-21 Zhewei Yao , Amir Gholami , Qi Lei , Kurt Keutzer , Michael W. Mahoney

Gradient descent (GD) and stochastic gradient descent (SGD) are the workhorses of large-scale machine learning. While classical theory focused on analyzing the performance of these methods in convex optimization problems, the most notable…

Machine Learning · Computer Science 2019-09-05 Chi Jin , Praneeth Netrapalli , Rong Ge , Sham M. Kakade , Michael I. Jordan

Learning a deep neural network requires solving a challenging optimization problem: it is a high-dimensional, non-convex and non-smooth minimization problem with a large number of terms. The current practice in neural network optimization…

Machine Learning · Computer Science 2021-02-23 Leonard Berrada , Andrew Zisserman , M. Pawan Kumar

It is widely believed that the implicit regularization of SGD is fundamental to the impressive generalization behavior we observe in neural networks. In this work, we demonstrate that non-stochastic full-batch training can achieve…

Machine Learning · Computer Science 2022-04-21 Jonas Geiping , Micah Goldblum , Phillip E. Pope , Michael Moeller , Tom Goldstein

It has been experimentally observed that distributed implementations of mini-batch stochastic gradient descent (SGD) algorithms exhibit speedup saturation and decaying generalization ability beyond a particular batch-size. In this work, we…

Machine Learning · Computer Science 2018-01-09 Dong Yin , Ashwin Pananjady , Max Lam , Dimitris Papailiopoulos , Kannan Ramchandran , Peter Bartlett

Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. However, due to…

Machine Learning · Computer Science 2017-01-17 Xi He , Dheevatsa Mudigere , Mikhail Smelyanskiy , Martin Takáč

In this technical report, we consider an approach that combines the PPO objective and K-FAC natural gradient optimization, for which we call PPOKFAC. We perform a range of empirical analysis on various aspects of the algorithm, such as…

Artificial Intelligence · Computer Science 2018-01-18 Jiaming Song , Yuhuai Wu

Although deep learning (DL) methods are powerful for solving inverse problems, their reliance on high-quality training data is a major hurdle. This is significant in high-dimensional (dynamic/volumetric) magnetic resonance imaging (MRI),…

Image and Video Processing · Electrical Eng. & Systems 2024-05-24 Frederic Wang , Han Qi , Alfredo De Goyeneche , Reinhard Heckel , Michael Lustig , Efrat Shimron