中文
相关论文

相关论文: On the Linear Speedup Analysis of Communication Ef…

200 篇论文

Decentralized training has been actively studied in recent years. Although a wide variety of methods have been proposed, yet the decentralized momentum SGD method is still underexplored. In this paper, we propose a novel periodic…

机器学习 · 计算机科学 2020-08-25 Hongchang Gao , Heng Huang

In this paper, we propose a method of distributed stochastic gradient descent (SGD), with low communication load and computational complexity, and still fast convergence. To reduce the communication load, at each iteration of the algorithm,…

机器学习 · 计算机科学 2020-03-30 Naeimeh Omidvar , Mohammad Ali Maddah-Ali , Hamed Mahdavi

Mini-batch stochastic gradient descent (SGD) is state of the art in large scale distributed training. The scheme can reach a linear speedup with respect to the number of workers, but this is rarely seen in practice as the scheme often…

最优化与控制 · 数学 2019-05-06 Sebastian U. Stich

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

With the increase in the amount of data and the expansion of model scale, distributed parallel training becomes an important and successful technique to address the optimization challenges. Nevertheless, although distributed stochastic…

机器学习 · 计算机科学 2019-09-23 Shuheng Shen , Linli Xu , Jingchang Liu , Xianfeng Liang , Yifei Cheng

Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent…

机器学习 · 统计学 2018-10-30 Ashok Cutkosky , Robert Busa-Fekete

Distributed stochastic gradient descent (SGD) is essential for scaling the machine learning algorithms to a large number of computing nodes. However, the infrastructures variability such as high communication delay or random node slowdown…

机器学习 · 计算机科学 2020-02-25 Jianyu Wang , Hao Liang , Gauri Joshi

In distributed training of deep neural networks, people usually run Stochastic Gradient Descent (SGD) or its variants on each machine and communicate with other machines periodically. However, SGD might converge slowly in training some deep…

机器学习 · 计算机科学 2022-10-14 Mingrui Liu , Zhenxun Zhuang , Yunwei Lei , Chunyang Liao

We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-convex and non-convex functions and derive concise, non-asymptotic, convergence rates. We show that the rate of convergence in all cases consists of two…

机器学习 · 计算机科学 2021-06-17 Sebastian U. Stich , Sai Praneeth Karimireddy

We consider large scale distributed optimization over a set of edge devices connected to a central server, where the limited communication bandwidth between the server and edge devices imposes a significant bottleneck for the optimization…

最优化与控制 · 数学 2021-12-28 Yujie Tang , Vikram Ramanathan , Junshan Zhang , Na Li

This paper studies distributed nonconvex optimization problems with stochastic gradients for a multi-agent system, in which each agent aims to minimize the sum of all agents' cost functions by using local compressed information exchange. We…

最优化与控制 · 数学 2024-03-05 Antai Xie , Xinlei Yi , Xiaofan Wang , Ming Cao , Xiaoqiang Ren

Stochastic Gradient Descent (SGD) is the most popular algorithm for training deep neural networks (DNNs). As larger networks and datasets cause longer training times, training on distributed systems is common and distributed SGD variants,…

机器学习 · 计算机科学 2019-06-17 Kwangmin Yu , Thomas Flynn , Shinjae Yoo , Nicholas D'Imperio

In this paper, we propose and analyze SQuARM-SGD, a communication-efficient algorithm for decentralized training of large-scale machine learning models over a network. In SQuARM-SGD, each node performs a fixed number of local SGD steps…

机器学习 · 计算机科学 2021-10-12 Navjot Singh , Deepesh Data , Jemin George , Suhas Diggavi

In recent years, distributed optimization is proven to be an effective approach to accelerate training of large scale machine learning models such as deep neural networks. With the increasing computation power of GPUs, the bottleneck of…

机器学习 · 计算机科学 2021-09-14 Xiangyi Chen , Xiaoyun Li , Ping Li

Distributed-memory implementations of numerical optimization algorithm, such as stochastic gradient descent (SGD), require interprocessor communication at every iteration of the algorithm. On modern distributed-memory clusters where…

分布式、并行与集群计算 · 计算机科学 2025-01-14 Aditya Devarakonda , Ramakrishnan Kannan

With the rapid increase of big data, distributed Machine Learning (ML) has been widely applied in training large-scale models. Stochastic Gradient Descent (SGD) is arguably the workhorse algorithm of ML. Distributed ML models trained by SGD…

机器学习 · 计算机科学 2021-12-09 Keyu Yang , Lu Chen , Zhihao Zeng , Yunjun Gao

The distributed nonconvex optimization problem of minimizing a global cost function formed by a sum of $n$ local cost functions by using local information exchange is considered. This problem is an important component of many machine…

最优化与控制 · 数学 2022-01-11 Xinlei Yi , Shengjun Zhang , Tao Yang , Tianyou Chai , Karl H. Johansson

For SGD based distributed stochastic optimization, computation complexity, measured by the convergence rate in terms of the number of stochastic gradient calls, and communication complexity, measured by the number of inter-node…

最优化与控制 · 数学 2019-05-14 Hao Yu , Rong Jin

Communication-efficient variants of SGD, specifically local SGD, have received a great deal of interest in recent years. These approaches compute multiple gradient steps locally on each worker, before averaging model parameters, helping…

机器学习 · 计算机科学 2025-06-13 Charles-Étienne Joseph , Benjamin Thérien , Abhinav Moudgil , Boris Knyazev , Eugene Belilovsky

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
‹ 上一页 1 2 3 10 下一页 ›