中文
相关论文

相关论文: A Unified Analysis of AdaGrad with Weighted Aggreg…

200 篇论文

Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some recent influential attempts would like to adaptively control…

机器学习 · 计算机科学 2020-10-22 Jie Liu , Chen Lin , Chuming Li , Lu Sheng , Ming Sun , Junjie Yan , Wanli Ouyang

Stochastic gradient descent (SGD) is an inherently sequential training algorithm--computing the gradient at batch $i$ depends on the model parameters learned from batch $i-1$. Prior approaches that break this dependence do not honor them…

分布式、并行与集群计算 · 计算机科学 2020-06-05 Saeed Maleki , Madan Musuvathi , Todd Mytkowicz , Olli Saarikivi , Tianju Xu , Vadim Eksarevskiy , Jaliya Ekanayake , Emad Barsoum

In this paper, we revisit stochastic gradient descent (SGD) with AdaGrad-type preconditioning. Our contributions are twofold. First, we develop a unified convergence analysis of SGD with adaptive preconditioning under anisotropic or matrix…

机器学习 · 计算机科学 2025-07-01 Dmitry Kovalev

Adaptive optimization methods such as AdaGrad, RMSprop and Adam have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared…

机器学习 · 计算机科学 2019-04-22 Liangchen Luo , Yuanhao Xiong , Yan Liu , Xu Sun

Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD)…

机器学习 · 计算机科学 2020-06-24 Jinghui Chen , Dongruo Zhou , Yiqi Tang , Ziyan Yang , Yuan Cao , Quanquan Gu

Heavy ball momentum is crucial in accelerating (stochastic) gradient-based optimization algorithms for machine learning. Existing heavy ball momentum is usually weighted by a uniform hyperparameter, which relies on excessive tuning.…

机器学习 · 计算机科学 2021-10-19 Tao Sun , Huaming Ling , Zuoqiang Shi , Dongsheng Li , Bao Wang

Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR) used by AGMs varies significantly across the dimensions of…

机器学习 · 计算机科学 2019-09-12 Qianqian Tong , Guannan Liang , Jinbo Bi

Adaptive gradient methods have become popular in optimizing deep neural networks; recent examples include AdaGrad and Adam. Although Adam usually converges faster, variations of Adam, for instance, the AdaBelief algorithm, have been…

机器学习 · 计算机科学 2024-10-29 Kushal Chakrabarti , Nikhil Chopra

For finite-sum optimization, variance-reduced gradient methods (VR) compute at each iteration the gradient of a single function (or of a mini-batch), and yet achieve faster convergence than SGD thanks to a carefully crafted lower-variance…

最优化与控制 · 数学 2024-04-09 Bastien Batardière , Joon Kwon

Stochastic Gradient Descent (SGD) and its variants are the most used algorithms in machine learning applications. In particular, SGD with adaptive learning rates and momentum is the industry standard to train deep networks. Despite the…

机器学习 · 统计学 2020-07-29 Xiaoyu Li , Francesco Orabona

Adaptive learning rate methods have been successfully applied in many fields, especially in training deep neural networks. Recent results have shown that adaptive methods with exponential increasing weights on squared past gradients (i.e.,…

机器学习 · 计算机科学 2021-01-05 Hui Zhong , Zaiyi Chen , Chuan Qin , Zai Huang , Vincent W. Zheng , Tong Xu , Enhong Chen

Adam and RMSProp are two of the most influential adaptive stochastic algorithms for training deep neural networks, which have been pointed out to be divergent even in the convex setting via a few simple counterexamples. Many attempts, such…

机器学习 · 计算机科学 2019-06-26 Fangyu Zou , Li Shen , Zequn Jie , Weizhong Zhang , Wei Liu

Adaptive gradient methods are workhorses in deep learning. However, the convergence guarantees of adaptive gradient methods for nonconvex optimization have not been thoroughly studied. In this paper, we provide a fine-grained convergence…

机器学习 · 计算机科学 2024-06-21 Dongruo Zhou , Jinghui Chen , Yuan Cao , Ziyan Yang , Quanquan Gu

Optimization algorithms with momentum, e.g., (ADAM), have been widely used for building deep learning models due to the faster convergence rates compared with stochastic gradient descent (SGD). Momentum helps accelerate SGD in the relevant…

机器学习 · 计算机科学 2020-01-24 Jiyang Bai , Yuxiang Ren , Jiawei Zhang

RMSProp and ADAM continue to be extremely popular algorithms for training neural nets but their theoretical convergence properties have remained unclear. Further, recent work has seemed to suggest that these algorithms have worse…

机器学习 · 计算机科学 2018-11-22 Soham De , Anirbit Mukherjee , Enayat Ullah

Adaptive gradient methods, especially Adam-type methods (such as Adam, AMSGrad, and AdaBound), have been proposed to speed up the training process with an element-wise scaling term on learning rates. However, they often generalize poorly…

机器学习 · 计算机科学 2021-07-20 Zhou Shao , Tong Lin

Adaptive gradient methods such as Adam have gained extreme popularity due to their success in training complex neural networks and less sensitivity to hyperparameter tuning compared to SGD. However, it has been recently shown that Adam can…

机器学习 · 计算机科学 2019-12-11 Pedro Savarese

Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks. Examples include AdaGrad, RMSProp, and Adam. We…

机器学习 · 统计学 2018-05-23 Ashia C. Wilson , Rebecca Roelofs , Mitchell Stern , Nathan Srebro , Benjamin Recht

In the context of stochastic gradient descent(SGD) and adaptive moment estimation (Adam),researchers have recently proposed optimization techniques that transition from Adam to SGD with the goal of improving both convergence and…

机器学习 · 计算机科学 2020-07-01 Jiaxuan Wang , Jenna Wiens

Adaptive gradient methods such as RMSProp and Adam use exponential moving estimate of the squared gradient to compute adaptive step sizes, achieving better convergence than SGD in face of noisy objectives. However, Adam can have undesirable…

机器学习 · 计算机科学 2021-07-06 Chen Zhu , Yu Cheng , Zhe Gan , Furong Huang , Jingjing Liu , Tom Goldstein
‹ 上一页 1 2 3 10 下一页 ›