English
Related papers

Related papers: Critical Bach Size Minimizes Stochastic First-Orde…

200 papers

Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers…

Machine Learning · Computer Science 2025-02-03 Ouya Wang , Shenglong Zhou , Geoffrey Ye Li

Adam is the go-to optimizer for training modern machine learning models, but it requires additional memory to maintain the moving averages of the gradients and their squares. While various low-memory optimizers have been proposed that…

Machine Learning · Computer Science 2025-03-19 Dayal Singh Kalra , John Kirchenbauer , Maissam Barkeshli , Tom Goldstein

Stochastic optimizers are central to deep learning, yet widely used methods such as Adam and Adan can degrade in non-stationary or noisy environments, partly due to their reliance on momentum-based magnitude estimates. We introduce Ano, a…

Machine Learning · Computer Science 2025-11-11 Adrien Kegreisz

An algorithm is presented for momentum gradient descent optimization based on the first-order differential equation of the Newtonian dynamics. The fictitious mass is introduced to the dynamics of momentum for regularizing the adaptive…

Machine Learning · Computer Science 2018-05-15 Zhidong Han

Adam has become one of the most popular optimizers for training modern deep neural networks, such as transformers. However, its applicability is largely restricted to single-level optimization problems. In this paper, we aim to extend…

Machine Learning · Computer Science 2025-03-07 Xiaochuan Gong , Jie Hao , Mingrui Liu

Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual learning, and reinforcement learning. Conventional BO…

Machine Learning · Computer Science 2022-09-20 Mao Ye , Bo Liu , Stephen Wright , Peter Stone , Qiang Liu

We explore an explicit link between stochastic gradient descent using common batching strategies and splitting methods for ordinary differential equations. From this perspective, we introduce a new minibatching strategy (called Symmetric…

Optimization and Control · Mathematics 2025-04-08 Luke Shaw , Peter A. Whalley

Distributed optimization is the standard way of speeding up machine learning training, and most of the research in the area focuses on distributed first-order, gradient-based methods. Yet, there are settings where some…

Machine Learning · Computer Science 2025-11-03 Matin Ansaripour , Shayan Talaei , Giorgi Nadiradze , Dan Alistarh

Mini-batch optimization has proven to be a powerful paradigm for large-scale learning. However, the state of the art parallel mini-batch algorithms assume synchronous operation or cyclic update orders. When worker nodes are heterogeneous…

Optimization and Control · Mathematics 2015-05-20 Hamid Reza Feyzmahdavian , Arda Aytekin , Mikael Johansson

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

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

Modern recommendation systems frequently employ online learning to dynamically update their models with freshly collected data. The most commonly used optimizer for updating neural networks in these contexts is the Adam optimizer, which…

Machine Learning · Computer Science 2025-06-05 Shaowen Wang , Anan Liu , Jian Xiao , Huan Liu , Yuekui Yang , Cong Xu , Qianqian Pu , Suncong Zheng , Wei Zhang , Di Wang , Jie Jiang , Jian Li

Stochastic estimators are fundamental to large-scale optimization, where population quantities must be inferred from noisy oracle observations. Although influential methods such as momentum, SPIDER, STORM, and PAGE have been highly…

Machine Learning · Computer Science 2026-05-18 Zhankun Luo , Antesh Upadhyay , M. Berk Sahin , Sang Bin Moon , Anuran Makur , Abolfazl Hashemi

Standard neural network training uses constant momentum (typically 0.9), a convention dating to 1964 with limited theoretical justification for its optimality. We derive a time-varying momentum schedule from the critically damped harmonic…

Machine Learning · Computer Science 2026-04-07 Ivan Pasichnyk

We study the role of an essential hyper-parameter that governs the training of Transformers for neural machine translation in a low-resource setting: the batch size. Using theoretical insights and experimental evidence, we argue against the…

Computation and Language · Computer Science 2022-03-22 Àlex R. Atrio , Andrei Popescu-Belis

With an increasing demand for training powers for deep learning algorithms and the rapid growth of computation resources in data centers, it is desirable to dynamically schedule different distributed deep learning tasks to maximize resource…

Machine Learning · Computer Science 2019-05-03 Haibin Lin , Hang Zhang , Yifei Ma , Tong He , Zhi Zhang , Sheng Zha , Mu Li

Fine-tuning large language models (LLMs) using standard first-order (FO) optimization often drives training toward sharp, poorly generalizing minima. Conversely, zeroth-order (ZO) methods offer stronger exploratory behavior without relying…

Machine Learning · Computer Science 2026-01-12 Feihu Jin , Ying Tan

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, and forms the bedrock of modern machine learning and statistics. In this work, we seek to balance the fact that attenuating step-size is…

Signal Processing · Electrical Eng. & Systems 2020-07-10 Zhan Gao , Alec Koppel , Alejandro Ribeiro

We investigate the role of the optimizer in determining the quality of the model fit for neural networks with a small to medium number of parameters. We study the performance of Adam, an algorithm for first-order gradient-based optimization…

Machine Learning · Computer Science 2022-05-17 John Taylor , Wenyi Wang , Biswajit Bala , Tomasz Bednarz

Focusing on the practical configuration needs of optimization algorithms in deep learning, this article concentrates on five major algorithms: SGD, Mini-batch SGD, Momentum, Adam, and Lion. It systematically analyzes the core advantages,…

Machine Learning · Computer Science 2025-11-27 Deng Fucheng , Wang Wanjie , Gong Ao , Wang Xiaoqi , Wang Fan