English
Related papers

Related papers: AdaShift: Decorrelation and Convergence of Adaptiv…

200 papers

The rapid scaling of large language models (LLMs) has made low-precision training essential for reducing memory, improving efficiency, and enabling larger models and datasets. Existing convergence theories for adaptive optimizers, however,…

Machine Learning · Computer Science 2026-03-03 Xuan Tang , Jichu Li , Difan Zou

Federated learning faces critical challenges in balancing communication efficiency and model accuracy. One key issue lies in the approximation of update errors without incurring high computational costs. In this paper, we propose a…

Machine Learning · Computer Science 2025-05-29 Ganglou Xu

The choice of step-size used in Stochastic Gradient Descent (SGD) optimization is empirically selected in most training procedures. Moreover, the use of scheduled learning techniques such as Step-Decaying, Cyclical-Learning, and Warmup to…

Machine Learning · Computer Science 2020-06-12 Mahdi S. Hosseini , Konstantinos N. Plataniotis

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

Stochastic gradient descent (SGD) has taken the stage as the primary workhorse for large-scale machine learning. It is often used with its adaptive variants such as AdaGrad, Adam, and AMSGrad. This paper proposes an adaptive stochastic…

Machine Learning · Computer Science 2021-01-01 Tianyi Chen , Ziye Guo , Yuejiao Sun , Wotao Yin

Adaptive gradient methods, such as AdaGrad, have become fundamental tools in deep learning. Despite their widespread use, the asymptotic convergence of AdaGrad remains poorly understood in non-convex scenarios. In this work, we present the…

Optimization and Control · Mathematics 2026-01-06 Ruinan Jin , Xiaoyu Wang

The dynamic behavior of RMSprop and Adam algorithms is studied through a combination of careful numerical experiments and theoretical explanations. Three types of qualitative features are observed in the training loss curve: fast initial…

Machine Learning · Computer Science 2021-10-01 Chao Ma , Lei Wu , Weinan E

Adam is a widely used optimization method for training deep learning models. It computes individual adaptive learning rates for different parameters. In this paper, we propose a generalization of Adam, called Adambs, that allows us to also…

Machine Learning · Computer Science 2020-10-27 Rui Liu , Tianyi Wu , Barzan Mozafari

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

In the training of neural networks, adaptive moment estimation (Adam) typically converges fast but exhibits suboptimal generalization performance. A widely accepted explanation for its defect in generalization is that it often tends to…

Machine Learning · Computer Science 2026-03-10 Tao Shi , Liangming Chen , Long Jin , Mengchu Zhou

Motivated by broad applications in machine learning, we study the popular accelerated stochastic gradient descent (ASGD) algorithm for solving (possibly nonconvex) optimization problems. We characterize the finite-time performance of this…

Optimization and Control · Mathematics 2020-10-20 Thinh T. Doan , Lam M. Nguyen , Nhan H. Pham , Justin Romberg

Convolutional neural networks (CNNs) are trained using stochastic gradient descent (SGD)-based optimizers. Recently, the adaptive moment estimation (Adam) optimizer has become very popular due to its adaptive momentum, which tackles the…

Machine Learning · Computer Science 2023-09-12 S. K. Roy , M. E. Paoletti , J. M. Haut , S. R. Dubey , P. Kar , A. Plaza , B. B. Chaudhuri

The choice of batch sizes in minibatch stochastic gradient optimizers is critical in large-scale model training for both optimization and generalization performance. Although large-batch training is arguably the dominant training paradigm…

Machine Learning · Computer Science 2024-05-29 Tim Tsz-Kit Lau , Han Liu , Mladen Kolar

In this paper, we try to uncover the second-order essence of several first-order optimization methods. For Nesterov Accelerated Gradient, we rigorously prove that the algorithm makes use of the difference between past and current gradients,…

Machine Learning · Computer Science 2019-12-23 Yuzheng Hu , Licong Lin , Shange Tang

While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings…

Optimization and Control · Mathematics 2020-10-26 Jingzhao Zhang , Sai Praneeth Karimireddy , Andreas Veit , Seungyeon Kim , Sashank J Reddi , Sanjiv Kumar , Suvrit Sra

Ever since Reddi et al. 2018 pointed out the divergence issue of Adam, many new variants have been designed to obtain convergence. However, vanilla Adam remains exceptionally popular and it works well in practice. Why is there a gap between…

Machine Learning · Computer Science 2023-01-16 Yushun Zhang , Congliang Chen , Naichen Shi , Ruoyu Sun , Zhi-Quan Luo

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter…

Machine Learning · Computer Science 2018-04-13 Noam Shazeer , Mitchell Stern

Adam is known to perform significantly better than Stochastic Gradient Descent (SGD) in language models, a phenomenon for which a number of explanations have been proposed. In this work, we revisit this "optimizer gap" through a series of…

Machine Learning · Computer Science 2025-06-17 Teodora Srećković , Jonas Geiping , Antonio Orvieto

The success of the Adam optimizer on a wide array of architectures has made it the default in settings where stochastic gradient descent (SGD) performs poorly. However, our theoretical understanding of this discrepancy is lagging,…

Machine Learning · Computer Science 2023-04-28 Frederik Kunstner , Jacques Chen , Jonathan Wilder Lavington , Mark Schmidt

Federated learning is a distributed and privacy-preserving approach to train a statistical model collaboratively from decentralized data of different parties. However, when datasets of participants are not independent and identically…

Machine Learning · Computer Science 2023-01-24 Li Ju , Tianru Zhang , Salman Toor , Andreas Hellander