中文
相关论文

相关论文: Averaged Adam accelerates stochastic optimization …

200 篇论文

Averaging techniques such as Ruppert--Polyak averaging and exponential movering averaging (EMA) are powerful approaches to accelerate optimization procedures of stochastic gradient descent (SGD) optimization methods such as the popular ADAM…

最优化与控制 · 数学 2025-05-29 Arnulf Jentzen , Julian Kranz , Adrian Riekert

It is known that the standard stochastic gradient descent (SGD) optimization method, as well as accelerated and adaptive SGD optimization methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (as,…

最优化与控制 · 数学 2024-06-21 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

Stochastic gradient descent (SGD) optimization methods are nowadays the method of choice for the training of deep neural networks (DNNs) in artificial intelligence systems. In practically relevant training problems, usually not the plain…

最优化与控制 · 数学 2024-08-01 Steffen Dereich , Arnulf Jentzen

Deep learning algorithms - typically consisting of a class of deep neural networks trained by a stochastic gradient descent (SGD) optimization method - are nowadays the key ingredients in many artificial intelligence (AI) systems and have…

机器学习 · 计算机科学 2024-07-12 Steffen Dereich , Robin Graeber , Arnulf Jentzen

First-order stochastic optimization methods are currently the most widely used class of methods for training deep neural networks. However, the choice of the optimizer has become an ad-hoc rule that can significantly affect the performance.…

机器学习 · 计算机科学 2020-10-21 Samy Jelassi , Aaron Defazio

Stochastic gradient descent (SGD) is the main approach for training deep networks: it moves towards the optimum of the cost function by iteratively updating the parameters of a model in the direction of the gradient of the loss evaluated on…

机器学习 · 计算机科学 2021-03-30 Loris Nanni , Gianluca Maguolo , Alessandra Lumini

Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization…

机器学习 · 计算机科学 2018-09-19 Zijun Zhang , Lin Ma , Zongpeng Li , Chuan Wu

The adaptive moment estimation (Adam) optimizer proposed by Kingma & Ba (2014) is presumably the most popular stochastic gradient descent (SGD) optimization method for the training of deep neural networks (DNNs) in artificial intelligence…

机器学习 · 计算机科学 2026-03-20 Steffen Dereich , Thang Do , Arnulf Jentzen

The stochastic gradient descent (SGD) optimizers are generally used to train the convolutional neural networks (CNNs). In recent years, several adaptive momentum based SGD optimizers have been introduced, such as Adam, diffGrad, Radam and…

计算机视觉与模式识别 · 计算机科学 2022-10-14 Shiv Ram Dubey , Satish Kumar Singh , Bidyut Baran Chaudhuri

Stochastic gradient descent (SGD) optimization methods such as the plain vanilla SGD method and the popular Adam optimizer are nowadays the method of choice in the training of artificial neural networks (ANNs). Despite the remarkable…

最优化与控制 · 数学 2024-02-09 Arnulf Jentzen , Adrian Riekert

Adam is a widely used stochastic optimization method for deep learning applications. While practitioners prefer Adam because it requires less parameter tuning, its use is problematic from a theoretical point of view since it may not…

机器学习 · 计算机科学 2020-11-25 Mingrui Liu , Wei Zhang , Francesco Orabona , Tianbao Yang

In this paper, we introduce StochGradAdam, a novel optimizer designed as an extension of the Adam algorithm, incorporating stochastic gradient sampling techniques to improve computational efficiency while maintaining robust performance.…

机器学习 · 计算机科学 2025-03-19 Juyoung Yun

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate…

机器学习 · 计算机科学 2019-12-04 Michael R. Zhang , James Lucas , Geoffrey Hinton , Jimmy Ba

We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quartic terms for kinetic energy with its stabilizing effects on various system dynamics. Previous…

机器学习 · 计算机科学 2026-05-13 Pranav Vaidhyanathan , Lucas Schorling , Natalia Ares , Michael A. Osborne

Despite the omnipresent use of stochastic gradient descent (SGD) optimization methods in the training of deep neural networks (DNNs), it remains, in basically all practically relevant scenarios, a fundamental open problem to provide a…

机器学习 · 计算机科学 2025-03-04 Thang Do , Arnulf Jentzen , Adrian Riekert

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

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed that compared with (stochastic) gradient descent, Adam can converge to a different solution with a…

机器学习 · 计算机科学 2021-08-26 Difan Zou , Yuan Cao , Yuanzhi Li , Quanquan Gu

Accelerated gradient-based methods are being extensively used for solving non-convex machine learning problems, especially when the data points are abundant or the available data is distributed across several agents. Two of the prominent…

机器学习 · 计算机科学 2021-10-04 Kushal Chakrabarti , Nikhil Chopra

Current state-of-the-art optimizers are adaptive gradient-based optimization methods such as Adam. Recently, there has been an increasing interest in formulating gradient-based optimizers in a probabilistic framework for better modeling the…

机器学习 · 计算机科学 2025-04-21 Haotian Chen , Anna Kuzina , Babak Esmaeili , Jakub M Tomczak

Adaptive gradient optimization methods, such as Adam, are prevalent in training deep neural networks across diverse machine learning tasks due to their ability to achieve faster convergence. However, these methods often suffer from…

机器学习 · 计算机科学 2025-02-12 Abulikemu Abuduweili , Changliu Liu
‹ 上一页 1 2 3 10 下一页 ›