English
Related papers

Related papers: Foxtsage vs. Adam: Revolution or Evolution in Opti…

200 papers

We present Amos, a stochastic gradient-based optimizer designed for training deep neural networks. It can be viewed as an Adam optimizer with theoretically supported, adaptive learning-rate decay and weight decay. A key insight behind Amos…

Machine Learning · Computer Science 2022-11-22 Ran Tian , Ankur P. Parikh

The Adam optimizer, often used in Machine Learning for neural network training, corresponds to an underlying ordinary differential equation (ODE) in the limit of very small learning rates. This work shows that the classical Adam algorithm…

Computational Engineering, Finance, and Science · Computer Science 2024-09-17 Abhinab Bhattacharjee , Andrey A. Popov , Arash Sarshar , Adrian Sandu

Deep neural networks are traditionally trained using human-designed stochastic optimization algorithms, such as SGD and Adam. Recently, the approach of learning to optimize network parameters has emerged as a promising research topic.…

Machine Learning · Computer Science 2018-11-26 Shipeng Wang , Jian Sun , Zongben Xu

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…

Machine Learning · Computer Science 2021-03-30 Loris Nanni , Gianluca Maguolo , Alessandra Lumini

A crucial component of machine learning algorithms is minimizing loss functions with less computational cost and less oscillations. While adaptive learning rate-based optimizers have been widely used for real-world tasks, they do not…

Machine Learning · Computer Science 2026-05-29 Sakshi Kumari , Shyam Kumar M , Sushmitha P

First-order optimization algorithms have been proven prominent in deep learning. In particular, algorithms such as RMSProp and Adam are extremely popular. However, recent works have pointed out the lack of ``long-term memory" in Adam-like…

Machine Learning · Computer Science 2020-12-01 Haiwen Huang , Chang Wang , Bin Dong

We introduce AlphaGrad, a memory-efficient, conditionally stateless optimizer addressing the memory overhead and hyperparameter complexity of adaptive methods like Adam. AlphaGrad enforces scale invariance via tensor-wise L2 gradient…

Machine Learning · Computer Science 2025-04-24 Soham Sane

We introduce ADAHESSIAN, a second order stochastic optimization algorithm which dynamically incorporates the curvature of the loss function via ADAptive estimates of the HESSIAN. Second order algorithms are among the most powerful…

Machine Learning · Computer Science 2021-04-30 Zhewei Yao , Amir Gholami , Sheng Shen , Mustafa Mustafa , Kurt Keutzer , Michael W. Mahoney

Adam has proven remarkable successful in training deep neural networks, but the mechanisms underlying its empirical successes and limitations remain underexplored. In this study, we demonstrate that the effectiveness of Adam stems largely…

Machine Learning · Computer Science 2025-07-10 Hanyang Peng , Shuang Qin , Yue Yu , Fangqing Jiang , Hui Wang , Wen Gao

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

The adaptive moment estimation algorithm Adam (Kingma and Ba) is a popular optimizer in the training of deep neural networks. However, Reddi et al. have recently shown that the convergence proof of Adam is problematic and proposed a variant…

Machine Learning · Computer Science 2019-11-01 Tran Thi Phuong , Le Trieu Phong

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…

Machine Learning · Computer Science 2026-03-20 Steffen Dereich , Thang Do , Arnulf Jentzen

Second-order optimization methods offer notable advantages in training deep neural networks by utilizing curvature information to achieve faster convergence. However, traditional second-order techniques are computationally prohibitive,…

Machine Learning · Computer Science 2024-10-04 James Vo

We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. This approach capitalizes on the inherent superposition property of wireless channels,…

Machine Learning · Computer Science 2024-03-12 Chenhao Wang , Zihan Chen , Nikolaos Pappas , Howard H. Yang , Tony Q. S. Quek , H. Vincent Poor

As deep learning models exponentially increase in size, optimizers such as Adam encounter significant memory consumption challenges due to the storage of first and second moment data. Current memory-efficient methods like Adafactor and CAME…

Machine Learning · Computer Science 2024-03-25 Pengxiang Zhao , Ping Li , Yingjie Gu , Yi Zheng , Stephan Ludger Kölker , Zhefeng Wang , Xiaoming Yuan

Standard mixed-precision training of neural networks requires many bytes of accelerator memory for each model parameter. These bytes reflect not just the parameter itself, but also its gradient and one or more optimizer state variables.…

Machine Learning · Computer Science 2026-03-13 Jose Javier Gonzalez Ortiz , Abhay Gupta , Christopher Rinard , Davis Blalock

Despite superior training outcomes, adaptive optimization methods such as Adam, Adagrad or RMSprop have been found to generalize poorly compared to Stochastic gradient descent (SGD). These methods tend to perform well in the initial portion…

Machine Learning · Computer Science 2017-12-21 Nitish Shirish Keskar , Richard Socher

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,…

Optimization and Control · Mathematics 2024-06-21 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

In this paper, we present a comprehensive study on the convergence properties of Adam-family methods for nonsmooth optimization, especially in the training of nonsmooth neural networks. We introduce a novel two-timescale framework that…

Optimization and Control · Mathematics 2024-02-20 Nachuan Xiao , Xiaoyin Hu , Xin Liu , Kim-Chuan Toh

Scalable training of large models (like BERT and GPT-3) requires careful optimization rooted in model design, architecture, and system capabilities. From a system standpoint, communication has become a major bottleneck, especially on…

Machine Learning · Computer Science 2021-07-01 Hanlin Tang , Shaoduo Gan , Ammar Ahmad Awan , Samyam Rajbhandari , Conglong Li , Xiangru Lian , Ji Liu , Ce Zhang , Yuxiong He