中文
相关论文

相关论文: Towards Theoretical Understanding of Large Batch T…

200 篇论文

Stochastic Gradient Descent (SGD) is a fundamental algorithm in machine learning, representing the optimization backbone for training several classic models, from regression to neural networks. Given the recent practical focus on…

分布式、并行与集群计算 · 计算机科学 2018-06-25 Dan Alistarh , Christopher De Sa , Nikola Konstantinov

Stochastic Gradient Descent (SGD) has proven to be remarkably effective in optimizing deep neural networks that employ ever-larger numbers of parameters. Yet, improving the efficiency of large-scale optimization remains a vital and highly…

机器学习 · 计算机科学 2020-11-11 Frithjof Gressmann , Zach Eaton-Rosen , Carlo Luschi

Stochastic Gradient Descent (SGD) is a known stochastic iterative method popular for large-scale convex optimization problems due to its simple implementation and scalability. Some objectives, such as those found in complex-valued neural…

机器学习 · 计算机科学 2026-05-26 Natanael Alpay , Emeric Battaglia

Motivated by broad applications in reinforcement learning and machine learning, this paper considers the popular stochastic gradient descent (SGD) when the gradients of the underlying objective function are sampled from Markov processes.…

最优化与控制 · 数学 2020-04-02 Thinh T. Doan , Lam M. Nguyen , Nhan H. Pham , Justin Romberg

One of the most common methods to train machine learning algorithms today is the stochastic gradient descent (SGD). In a distributed setting, SGD-based algorithms have been shown to converge theoretically under specific circumstances. A…

机器学习 · 计算机科学 2025-08-22 Soumya Sarkar , Shweta Jain

SketchySGD improves upon existing stochastic gradient methods in machine learning by using randomized low-rank approximations to the subsampled Hessian and by introducing an automated stepsize that works well across a wide range of convex…

最优化与控制 · 数学 2024-02-22 Zachary Frangella , Pratik Rathore , Shipu Zhao , Madeleine Udell

Stochastic gradient descent (SGD) is a widely adopted iterative method for optimizing differentiable objective functions. In this paper, we propose and discuss a novel approach to scale up SGD in applications involving non-convex functions…

机器学习 · 统计学 2022-10-07 Saad Mohamad , Hamad Alamri , Abdelhamid Bouchachia

As one of the most fundamental stochastic optimization algorithms, stochastic gradient descent (SGD) has been intensively developed and extensively applied in machine learning in the past decade. There have been some modified SGD-type…

机器学习 · 计算机科学 2022-01-28 Ruinan Jin , Yu Xing , Xingkang He

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…

机器学习 · 计算机科学 2020-09-02 Xin Zhang , Jia Liu , Zhengyuan Zhu

Nesterov SGD is widely used for training modern neural networks and other machine learning models. Yet, its advantages over SGD have not been theoretically clarified. Indeed, as we show in our paper, both theoretically and empirically,…

机器学习 · 计算机科学 2019-09-30 Chaoyue Liu , Mikhail Belkin

Stochastic gradient descent (SGD) is a prevalent optimization technique for large-scale distributed machine learning. While SGD computation can be efficiently divided between multiple machines, communication typically becomes a bottleneck…

机器学习 · 计算机科学 2021-05-24 Dmitrii Avdiukhin , Grigory Yaroslavtsev

Modern deep networks are trained with stochastic gradient descent (SGD) whose key hyperparameters are the number of data considered at each step or batch size $B$, and the step size or learning rate $\eta$. For small $B$ and large $\eta$,…

机器学习 · 计算机科学 2024-02-29 Antonio Sclocchi , Matthieu Wyart

We study the generalization properties of the popular stochastic optimization method known as stochastic gradient descent (SGD) for optimizing general non-convex loss functions. Our main contribution is providing upper bounds on the…

机器学习 · 计算机科学 2021-08-17 Gergely Neu , Gintare Karolina Dziugaite , Mahdi Haghifam , Daniel M. Roy

Modern machine learning often requires training with large batch size, distributed data, and massively parallel compute hardware (like mobile and other edge devices or distributed data centers). Communication becomes a major bottleneck in…

机器学习 · 计算机科学 2025-12-12 Ahmed Khaled , Satyen Kale , Arthur Douillard , Chi Jin , Rob Fergus , Manzil Zaheer

While stochastic gradient descent (SGD) and variants have been surprisingly successful for training deep nets, several aspects of the optimization dynamics and generalization are still not well understood. In this paper, we present new…

机器学习 · 计算机科学 2019-07-26 Xinyan Li , Qilong Gu , Yingxue Zhou , Tiancong Chen , Arindam Banerjee

This paper presents fault-tolerant asynchronous Stochastic Gradient Descent (SGD) algorithms. SGD is widely used for approximating the minimum of a cost function $Q$, as a core part of optimization and learning algorithms. Our algorithms…

分布式、并行与集群计算 · 计算机科学 2023-06-14 Hagit Attiya , Noa Schiller

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

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…

机器学习 · 计算机科学 2025-10-14 Kanata Oowada , Hideaki Iiduka

Most modern learning problems are highly overparameterized, meaning that there are many more parameters than the number of training data points, and as a result, the training loss may have infinitely many global minima (parameter vectors…

机器学习 · 计算机科学 2019-06-11 Navid Azizan , Sahin Lale , Babak Hassibi

Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the dynamics of stochastic gradient descent over diagonal linear…

机器学习 · 计算机科学 2021-12-08 Scott Pesme , Loucas Pillaud-Vivien , Nicolas Flammarion