English
Related papers

Related papers: Investigating Alternatives to the Root Mean Square…

200 papers

Despite their popularity in deep learning and machine learning in general, the theoretical properties of adaptive optimizers such as Adagrad, RMSProp, Adam or AdamW are not yet fully understood. In this paper, we develop a novel framework…

Machine Learning · Computer Science 2022-11-09 Han Nguyen , Hai Pham , Sashank J. Reddi , Barnabás Póczos

It is widely believed that stochastic gradient descent (SGD) performs significantly worse than adaptive optimizers such as Adam in pre-training Large Language Models (LLMs). Yet the underlying reason for this gap remains unclear. In this…

Machine Learning · Computer Science 2026-05-19 Athanasios Glentis , Dawei Li , Chung-Yiu Yau , Mingyi Hong

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…

Machine Learning · Computer Science 2024-06-21 Dongruo Zhou , Jinghui Chen , Yuan Cao , Ziyan Yang , Quanquan Gu

Methods with adaptive scaling of different features play a key role in solving saddle point problems, primarily due to Adam's popularity for solving adversarial machine learning problems, including GANS training. This paper carries out a…

Machine Learning · Computer Science 2023-06-22 Aleksandr Beznosikov , Aibek Alanov , Dmitry Kovalev , Martin Takáč , Alexander Gasnikov

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…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-05 Saeed Maleki , Madan Musuvathi , Todd Mytkowicz , Olli Saarikivi , Tianju Xu , Vadim Eksarevskiy , Jaliya Ekanayake , Emad Barsoum

Adaptive gradient methods have achieved remarkable success in training deep neural networks on a wide variety of tasks. However, not much is known about the mathematical and statistical properties of this family of methods. This work aims…

Machine Learning · Computer Science 2021-05-18 Zhang Zhiyi , Liu Ziyin

Adam is shown not being able to converge to the optimal solution in certain cases. Researchers recently propose several algorithms to avoid the issue of non-convergence of Adam, but their efficiency turns out to be unsatisfactory in…

Machine Learning · Computer Science 2019-06-25 Zhiming Zhou , Qingru Zhang , Guansong Lu , Hongwei Wang , Weinan Zhang , Yong Yu

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…

Machine Learning · Computer Science 2018-11-22 Soham De , Anirbit Mukherjee , Enayat Ullah

Adaptive optimization algorithms -- such as Adagrad, Adam, and their variants -- have found widespread use in machine learning, signal processing and many other settings. Several methods in this family are not rotationally equivariant,…

Machine Learning · Computer Science 2026-02-17 Adela DePavia , Jose Cruzado , Jiayou Liang , Vasileios Charisopoulos , Rebecca Willett

In current deep learning tasks, Adam style optimizers such as Adam, Adagrad, RMSProp, Adafactor, and Lion have been widely used as alternatives to SGD style optimizers. These optimizers typically update model parameters using the sign of…

Machine Learning · Computer Science 2024-10-29 Shuaipeng Li , Penghao Zhao , Hailin Zhang , Xingwu Sun , Hao Wu , Dian Jiao , Weiyan Wang , Chengjun Liu , Zheng Fang , Jinbao Xue , Yangyu Tao , Bin Cui , Di Wang

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…

Machine Learning · Computer Science 2020-07-01 Jiaxuan Wang , Jenna Wiens

In this paper, we provide a rigorous proof of convergence of the Adaptive Moment Estimate (Adam) algorithm for a wide class of optimization objectives. Despite the popularity and efficiency of the Adam algorithm in training deep neural…

Optimization and Control · Mathematics 2023-11-08 Haochuan Li , Alexander Rakhlin , Ali Jadbabaie

We implement the adaptive step size scheme from the optimization methods AdaGrad and Adam in a novel variant of the Proximal Gradient Method (PGM). Our algorithm, dubbed AdaProx, avoids the need for explicit computation of the Lipschitz…

Optimization and Control · Mathematics 2020-07-06 Peter Melchior , Rémy Joseph , Fred Moolekamp

We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has…

Machine Learning · Computer Science 2017-01-31 Diederik P. Kingma , Jimmy Ba

Gradient descent based optimization methods are the methods of choice to train deep neural networks in machine learning. Beyond the standard gradient descent method, also suitable modified variants of standard gradient descent involving…

Optimization and Control · Mathematics 2025-04-29 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

Adaptive optimizers, most notably Adam, have become the default standard for training large-scale neural networks such as Transformers. These methods maintain running estimates of gradient first and second moments, incurring substantial…

Machine Learning · Computer Science 2026-05-12 Yao Lu , Dengdong Fan , Shixun Zhang , Yonghong Tian

Root mean square propagation (abbreviated as RMSProp) is a first-order stochastic algorithm used in machine learning widely. In this paper, a stable gradient-adjusted RMSProp (abbreviated as SGA-RMSProp) with mini-batch stochastic gradient…

Optimization and Control · Mathematics 2025-07-28 Runze Li , Jintao Xu , Wenxun Xing

Despite its widespread adoption, Adam's advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This paper investigates Adam's sensitivity to rotations of the parameter space. We observe that Adam's…

Accelerated training algorithms, such as adaptive learning rates (or preconditioning) and various normalization methods, are widely used but not fully understood. When regularization is introduced, standard optimizers like adaptive learning…

Machine Learning · Computer Science 2025-12-30 Qiang Ye

Since its invention in 2014, the Adam optimizer has received tremendous attention. On one hand, it has been widely used in deep learning and many variants have been proposed, while on the other hand their theoretical convergence property…

Machine Learning · Computer Science 2021-12-08 Zhishuai Guo , Yi Xu , Wotao Yin , Rong Jin , Tianbao Yang
‹ Prev 1 3 4 5 6 7 10 Next ›