中文
相关论文

相关论文: Special Properties of Gradient Descent with Large …

200 篇论文

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…

机器学习 · 计算机科学 2023-06-08 Maksym Andriushchenko , Aditya Varre , Loucas Pillaud-Vivien , Nicolas Flammarion

Stochastic gradient descent (SGD) is a popular and efficient method with wide applications in training deep neural nets and other nonconvex models. While the behavior of SGD is well understood in the convex learning setting, the existing…

机器学习 · 计算机科学 2019-12-16 Yunwen Lei , Ting Hu , Guiying Li , Ke Tang

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

In machine learning, stochastic gradient descent (SGD) is widely deployed to train models using highly non-convex objectives with equally complex noise models. Unfortunately, SGD theory often makes restrictive assumptions that fail to…

机器学习 · 计算机科学 2022-10-11 Vivak Patel , Shushu Zhang , Bowen Tian

Stochastic Gradient Descent (SGD) based training of neural networks with a large learning rate or a small batch-size typically ends in well-generalizing, flat regions of the weight space, as indicated by small eigenvalues of the Hessian of…

Momentum is known to accelerate the convergence of gradient descent in strongly convex settings without stochastic gradient noise. In stochastic optimization, such as training neural networks, folklore suggests that momentum may help deep…

机器学习 · 计算机科学 2024-04-17 Runzhe Wang , Sadhika Malladi , Tianhao Wang , Kaifeng Lyu , Zhiyuan Li

Stochastic gradient descent~(SGD) and its variants have been the dominating optimization methods in machine learning. Compared to SGD with small-batch training, SGD with large-batch training can better utilize the computational power of…

机器学习 · 统计学 2024-04-16 Shen-Yi Zhao , Chang-Wei Shi , Yin-Peng Xie , Wu-Jun Li

Stochastic gradient descent is the method of choice for large scale optimization of machine learning objective functions. Yet, its performance is greatly variable and heavily depends on the choice of the stepsizes. This has motivated a…

机器学习 · 统计学 2019-02-28 Xiaoyu Li , Francesco Orabona

The convergence of stochastic gradient descent is highly dependent on the step-size, especially on non-convex problems such as neural network training. Step decay step-size schedules (constant and then cut) are widely used in practice…

最优化与控制 · 数学 2021-02-19 Xiaoyu Wang , Sindri Magnússon , Mikael Johansson

Recent works have shown that high probability metrics with stochastic gradient descent (SGD) exhibit informativeness and in some cases advantage over the commonly adopted mean-square error-based ones. In this work we provide a formal…

机器学习 · 计算机科学 2022-11-03 Dragana Bajovic , Dusan Jakovetic , Soummya Kar

Stochastic gradient descent (SGD) has been found to be surprisingly effective in training a variety of deep neural networks. However, there is still a lack of understanding on how and why SGD can train these complex networks towards a…

机器学习 · 计算机科学 2019-01-03 Yi Zhou , Junjie Yang , Huishuai Zhang , Yingbin Liang , Vahid Tarokh

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

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…

机器学习 · 统计学 2024-09-20 Ossi Räisä , Joonas Jälkö , Antti Honkela

Stochastic gradient descent (SGD) is almost ubiquitously used for training non-convex optimization tasks. Recently, a hypothesis proposed by Keskar et al. [2017] that large batch methods tend to converge to sharp minimizers has received…

机器学习 · 统计学 2018-12-04 Xiaowu Dai , Yuhua Zhu

Stochastic Gradient Descent (SGD) is widely used in machine learning research. Previous convergence analyses of SGD under the vanishing step-size setting typically require Robbins-Monro conditions. However, in practice, a wider variety of…

机器学习 · 计算机科学 2025-04-18 Ruinan Jin , Difei Cheng , Hong Qiao , Xin Shi , Shaodong Liu , Bo Zhang

Differentially private stochastic gradient descent (DP-SGD) is known to have poorer training and test performance on large neural networks, compared to ordinary stochastic gradient descent (SGD). In this paper, we perform a detailed study…

机器学习 · 计算机科学 2023-11-14 Lauren Watson , Eric Gan , Mohan Dantam , Baharan Mirzasoleiman , Rik Sarkar

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…

机器学习 · 计算机科学 2020-06-29 Samuel L. Smith , Erich Elsen , Soham De

Classical stochastic gradient methods for optimization rely on noisy gradient approximations that become progressively less accurate as iterates approach a solution. The large noise and small signal in the resulting gradients makes it…

机器学习 · 计算机科学 2017-04-10 Soham De , Abhay Yadav , David Jacobs , Tom Goldstein

Stochastic gradient descent (SGD) is one of the most popular algorithms in modern machine learning. The noise encountered in these applications is different from that in many theoretical analyses of stochastic gradient algorithms. In this…

机器学习 · 统计学 2021-09-16 Stephan Wojtowytsch

Training Deep Neural Networks (DNNs) with small batches using Stochastic Gradient Descent (SGD) yields superior test performance compared to larger batches. The specific noise structure inherent to SGD is known to be responsible for this…

机器学习 · 统计学 2024-02-14 Tom Sander , Maxime Sylvestre , Alain Durmus
‹ 上一页 1 2 3 10 下一页 ›