English
Related papers

Related papers: Subsampling is not Magic: Why Large Batch Sizes Wo…

200 papers

This paper presents a novel adaptation of the Stochastic Gradient Descent (SGD), termed AdaBatchGrad. This modification seamlessly integrates an adaptive step size with an adjustable batch size. An increase in batch size and a decrease in…

Machine Learning · Computer Science 2024-02-09 Petr Ostroukhov , Aigerim Zhumabayeva , Chulu Xiang , Alexander Gasnikov , Martin Takáč , Dmitry Kamzolov

The performance of stochastic gradient descent (SGD), which is the simplest first-order optimizer for training deep neural networks, depends on not only the learning rate but also the batch size. They both affect the number of iterations…

Machine Learning · Statistics 2024-02-26 Kento Imaizumi , Hideaki Iiduka

We propose a new framework, inspired by random matrix theory, for analyzing the dynamics of stochastic gradient descent (SGD) when both number of samples and dimensions are large. This framework applies to any fixed stepsize and the finite…

Optimization and Control · Mathematics 2021-02-09 Courtney Paquette , Kiwon Lee , Fabian Pedregosa , Elliot Paquette

Stochastic variance-reduced gradient (SVRG) is a classical optimization method. Although it is theoretically proved to have better convergence performance than stochastic gradient descent (SGD), the generalization performance of SVRG…

Machine Learning · Statistics 2019-08-20 Hao Jin , Dachao Lin , Zhihua Zhang

As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient…

Machine Learning · Computer Science 2023-11-15 Badih Ghazi , Yangsibo Huang , Pritish Kamath , Ravi Kumar , Pasin Manurangsi , Amer Sinha , Chiyuan Zhang

Stochastic gradient descent (SGD) is a widely adopted iterative method for optimizing differentiable objective functions. In this paper, we propose and discuss a novel approach to scale up SGD in applications involving non-convex functions…

Machine Learning · Statistics 2022-10-07 Saad Mohamad , Hamad Alamri , Abdelhamid Bouchachia

The choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on accelerating convergence and reducing the effects of the…

Computation and Language · Computer Science 2020-05-06 Hongfei Xu , Josef van Genabith , Deyi Xiong , Qiuhui Liu

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

The impact of gradient noise on training deep models is widely acknowledged but not well understood. In this context, we study the distribution of gradients during training. We introduce a method, Gradient Clustering, to minimize the…

Machine Learning · Computer Science 2020-07-10 Fartash Faghri , David Duvenaud , David J. Fleet , Jimmy Ba

The use of low-bit quantization has emerged as an indispensable technique for enabling the efficient training of large-scale models. Despite its widespread empirical success, a rigorous theoretical understanding of its impact on learning…

Machine Learning · Statistics 2026-02-17 Dechen Zhang , Junwei Su , Difan Zou

Mini-batch stochastic gradient descent (SGD) is state of the art in large scale distributed training. The scheme can reach a linear speedup with respect to the number of workers, but this is rarely seen in practice as the scheme often…

Optimization and Control · Mathematics 2019-05-06 Sebastian U. Stich

Conventional wisdom dictates that small batch sizes make language model pretraining and fine-tuning unstable, motivating gradient accumulation, which trades off the number of optimizer steps for a proportional increase in batch size. While…

Machine Learning · Computer Science 2025-12-17 Martin Marek , Sanae Lotfi , Aditya Somasundaram , Andrew Gordon Wilson , Micah Goldblum

We consider two questions at the heart of machine learning; how can we predict if a minimum will generalize to the test set, and why does stochastic gradient descent find minima that generalize well? Our work responds to Zhang et al.…

Machine Learning · Computer Science 2018-02-16 Samuel L. Smith , Quoc V. Le

Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, provides a principled framework for training LLMs with…

Machine Learning · Computer Science 2026-05-26 Enayat Ullah , Sai Aparna Aketi , Devansh Gupta , Huanyu Zhang , Meisam Razaviyayn

Differentially Private (DP) learning has seen limited success for building large deep learning models of text, and straightforward attempts at applying Differentially Private Stochastic Gradient Descent (DP-SGD) to NLP tasks have resulted…

Machine Learning · Computer Science 2022-11-11 Xuechen Li , Florian Tramèr , Percy Liang , Tatsunori Hashimoto

We theoretically analyzed the convergence behavior of Riemannian stochastic gradient descent (RSGD) and found that using an increasing batch size leads to faster convergence than using a constant batch size, not only with a constant…

Machine Learning · Computer Science 2025-10-14 Kanata Oowada , Hideaki Iiduka

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

Differentially private stochastic gradient descent (DP-SGD) is the gold standard for training machine learning models with formal differential privacy guarantees. Several recent extensions improve its accuracy by introducing correlated…

Machine Learning · Computer Science 2026-05-13 Nikita P. Kalinin , Ryan McKenna , Rasmus Pagh , Christoph H. Lampert

In the vanishing learning rate regime, stochastic gradient descent (SGD) is now relatively well understood. In this work, we propose to study the basic properties of SGD and its variants in the non-vanishing learning rate regime. The focus…

Machine Learning · Statistics 2021-06-14 Kangqiao Liu , Liu Ziyin , Masahito Ueda

We study the power of learning via mini-batch stochastic gradient descent (SGD) on the population loss, and batch Gradient Descent (GD) on the empirical loss, of a differentiable model or neural network, and ask what learning problems can…

Machine Learning · Computer Science 2022-02-08 Emmanuel Abbe , Pritish Kamath , Eran Malach , Colin Sandon , Nathan Srebro
‹ Prev 1 3 4 5 6 7 10 Next ›