中文
相关论文

相关论文: The Impact of the Mini-batch Size on the Variance …

200 篇论文

The performance of mini-batch stochastic gradient descent (SGD) strongly depends on setting the batch size and learning rate to minimize the empirical loss in training the deep neural network. In this paper, we present theoretical analyses…

机器学习 · 计算机科学 2025-02-17 Hikaru Umeda , Hideaki Iiduka

Mini-batch stochastic gradient descent (SGD) and variants thereof approximate the objective function's gradient with a small number of training examples, aka the batch size. Small batch sizes require little computation for each model update…

机器学习 · 计算机科学 2023-09-28 Scott Sievert , Shrey Shah

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…

Stochastic gradient descent plays a fundamental role in nearly all applications of deep learning. However its ability to converge to a global minimum remains shrouded in mystery. In this paper we propose to study the behavior of the loss…

机器学习 · 计算机科学 2023-02-02 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Nolan Miller

The stochastic gradient descent (SGD) algorithm is the algorithm we use to train neural networks. However, it remains poorly understood how the SGD navigates the highly nonlinear and degenerate loss landscape of a neural network. In this…

机器学习 · 计算机科学 2025-06-13 Liu Ziyin , Hongchao Li , Masahito Ueda

Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However,…

机器学习 · 计算机科学 2020-02-18 Tao Lin , Sebastian U. Stich , Kumar Kshitij Patel , Martin Jaggi

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

机器学习 · 计算机科学 2018-01-17 Pratik Chaudhari , Stefano Soatto

We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a…

机器学习 · 计算机科学 2024-10-22 Tomer Galanti , Zachary S. Siegel , Aparna Gupte , Tomaso Poggio

The noise in stochastic gradient descent (SGD), caused by minibatch sampling, is poorly understood despite its practical importance in deep learning. This work presents the first systematic study of the SGD noise and fluctuations close to a…

机器学习 · 计算机科学 2022-03-09 Liu Ziyin , Kangqiao Liu , Takashi Mori , Masahito Ueda

Stochastic Gradient Descent (SGD) is the workhorse algorithm of deep learning technology. At each step of the training phase, a mini batch of samples is drawn from the training dataset and the weights of the neural network are adjusted…

无序系统与神经网络 · 物理学 2022-09-07 Francesca Mignacco , Pierfrancesco Urbani

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…

机器学习 · 计算机科学 2025-09-25 Keisuke Kamo , Hideaki Iiduka

Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Mini-batch SGD is one of the most popular stochastic optimization…

机器学习 · 计算机科学 2019-03-12 Xinyu Peng , Li Li , Fei-Yue Wang

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…

机器学习 · 计算机科学 2018-01-09 Dong Yin , Ashwin Pananjady , Max Lam , Dimitris Papailiopoulos , Kannan Ramchandran , Peter Bartlett

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…

In this work, we investigate the dynamics of stochastic gradient descent (SGD) when training a single-neuron autoencoder with linear or ReLU activation on orthogonal data. We show that for this non-convex problem, randomly initialized SGD…

机器学习 · 统计学 2023-08-08 Nikhil Ghosh , Spencer Frei , Wooseok Ha , Bin Yu

We propose a projected semi-stochastic gradient descent method with mini-batch for improving both the theoretical complexity and practical performance of the general stochastic gradient descent method (SGD). We are able to prove linear…

机器学习 · 计算机科学 2017-05-08 Jie Liu , Martin Takac

Stochastic gradient descent (SGD) and its variants have established themselves as the go-to algorithms for large-scale machine learning problems with independent samples due to their generalization performance and intrinsic computational…

机器学习 · 统计学 2025-08-25 Hao Chen , Lili Zheng , Raed Al Kontar , Garvesh Raskutti

Stochastic Gradient Descent (SGD) is a central tool in machine learning. We prove that SGD converges to zero loss, even with a fixed (non-vanishing) learning rate - in the special case of homogeneous linear classifiers with smooth monotone…

机器学习 · 统计学 2022-04-19 Mor Shpigel Nacson , Nathan Srebro , Daniel Soudry

We study the Stochastic Gradient Descent (SGD) method in nonconvex optimization problems from the point of view of approximating diffusion processes. We prove rigorously that the diffusion process can approximate the SGD algorithm weakly…

机器学习 · 统计学 2018-03-06 Wenqing Hu , Chris Junchi Li , Lei Li , Jian-Guo Liu

Stochastic gradient descent (SGD) is widely used in machine learning. Although being commonly viewed as a fast but not accurate version of gradient descent (GD), it always finds better solutions than GD for modern neural networks. In order…

机器学习 · 计算机科学 2018-08-17 Robert Kleinberg , Yuanzhi Li , Yang Yuan
‹ 上一页 1 2 3 10 下一页 ›