English
Related papers

Related papers: SWAN: SGD with Normalization and Whitening Enables…

200 papers

LLM training is resource-intensive. Quantized training improves computational and memory efficiency but introduces quantization noise, which can hinder convergence and degrade model accuracy. Stochastic Rounding (SR) has emerged as a…

Machine Learning · Computer Science 2025-11-04 Taowen Liu , Marta Andronic , Deniz Gündüz , George A. Constantinides

Adam has been widely adopted for training deep neural networks due to less hyperparameter tuning and remarkable performance. To improve generalization, Adam is typically used in tandem with a squared $\ell_2$ regularizer (referred to as…

Machine Learning · Computer Science 2022-02-02 Zhenxun Zhuang , Mingrui Liu , Ashok Cutkosky , Francesco Orabona

Lowering the memory requirement in full-parameter training on large models has become a hot research area. MeZO fine-tunes the large language models (LLMs) by just forward passes in a zeroth-order SGD optimizer (ZO-SGD), demonstrating…

Machine Learning · Computer Science 2023-12-27 Shuoran Jiang , Qingcai Chen , Youchen Pan , Yang Xiang , Yukang Lin , Xiangping Wu , Chuanyi Liu , Xiaobao Song

We introduce two complementary techniques for efficient optimization that reduce memory requirements while accelerating training of large-scale neural networks. The first technique, Subset-Norm step size, generalizes AdaGrad-Norm and…

Machine Learning · Computer Science 2025-05-27 Thien Hang Nguyen , Huy Le Nguyen

Stochastic Gradient Descent or SGD is the most popular optimization algorithm for large-scale problems. SGD estimates the gradient by uniform sampling with sample size one. There have been several other works that suggest faster epoch-wise…

Machine Learning · Computer Science 2019-11-01 Beidi Chen , Yingchen Xu , Anshumali Shrivastava

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

Adam is the de facto optimization algorithm for several deep learning applications, but an understanding of its implicit bias and how it differs from other algorithms, particularly standard first-order methods such as (stochastic) gradient…

Machine Learning · Computer Science 2025-10-27 Bhavya Vasudeva , Jung Whan Lee , Vatsal Sharan , Mahdi Soltanolkotabi

Communication-efficient variants of SGD, specifically local SGD, have received a great deal of interest in recent years. These approaches compute multiple gradient steps locally on each worker, before averaging model parameters, helping…

Machine Learning · Computer Science 2025-06-13 Charles-Étienne Joseph , Benjamin Thérien , Abhinav Moudgil , Boris Knyazev , Eugene Belilovsky

Modern machine learning is trained by stochastic gradient descent (SGD), whose performance critically depends on how the learning rate (LR) is adjusted and decreased over time. Yet existing LR regimes may be intricate, or need to tune one…

Machine Learning · Computer Science 2025-08-20 Zhuang Yang

In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks, especially large language models. However, the use of adaptivity not only comes at the cost of extra memory but also raises the…

Machine Learning · Computer Science 2022-07-20 Zhiyuan Li , Srinadh Bhojanapalli , Manzil Zaheer , Sashank J. Reddi , Sanjiv Kumar

Gradient descent (GD) based optimization methods are these days the standard tools to train deep neural networks in artificial intelligence systems. In optimization procedures in deep learning the employed optimizer is often not the…

Optimization and Control · Mathematics 2025-09-24 Steffen Dereich , Robin Graeber , Arnulf Jentzen , Adrian Riekert

In practice, the hyperparameters $(\beta_1, \beta_2)$ and weight-decay $\lambda$ in AdamW are typically kept at fixed values. Is there any reason to do otherwise? We show that for large-scale language model training, the answer is yes: by…

Machine Learning · Statistics 2026-02-19 Damien Ferbach , Courtney Paquette , Gauthier Gidel , Katie Everett , Elliot Paquette

Adaptive gradient methods have become popular in optimizing deep neural networks; recent examples include AdaGrad and Adam. Although Adam usually converges faster, variations of Adam, for instance, the AdaBelief algorithm, have been…

Machine Learning · Computer Science 2024-10-29 Kushal Chakrabarti , Nikhil Chopra

Deep neural networks (DNNs) have achieved remarkable success in computer vision; however, training DNNs for satisfactory performance remains challenging and suffers from sensitivity to empirical selections of an optimization algorithm for…

Computer Vision and Pattern Recognition · Computer Science 2020-12-22 Haichao Zhang , Kuangrong Hao , Lei Gao , Bing Wei , Xuesong Tang

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

In overparametrized models, the noise in stochastic gradient descent (SGD) implicitly regularizes the optimization trajectory and determines which local minimum SGD converges to. Motivated by empirical studies that demonstrate that training…

Machine Learning · Computer Science 2021-12-07 Alex Damian , Tengyu Ma , Jason D. Lee

The Warmup Stable Decay (WSD) learning rate scheduler has recently become popular, largely due to its good performance and flexibility when training large language models. It remains an open question whether the remarkable performance of…

Machine Learning · Computer Science 2026-01-15 Annalisa Belloni , Lorenzo Noci , Antonio Orvieto

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…

Machine Learning · Computer Science 2020-11-25 Mingrui Liu , Wei Zhang , Francesco Orabona , Tianbao Yang

Local SGD is a promising approach to overcome the communication overhead in distributed learning by reducing the synchronization frequency among worker nodes. Despite the recent theoretical advances of local SGD in empirical risk…

Machine Learning · Computer Science 2021-03-01 Yuyang Deng , Mehrdad Mahdavi

Adaptive methods are a crucial component widely used for training generative adversarial networks (GANs). While there has been some work to pinpoint the "marginal value of adaptive methods" in standard tasks, it remains unclear why they are…

Machine Learning · Computer Science 2022-10-11 Samy Jelassi , David Dobre , Arthur Mensch , Yuanzhi Li , Gauthier Gidel