English
Related papers

Related papers: Learning Rates as a Function of Batch Size: A Rand…

200 papers

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

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

Investigating the dynamics of learning in machine learning algorithms is of paramount importance for understanding how and why an approach may be successful. The tools of physics and statistics provide a robust setting for such…

High Energy Physics - Lattice · Physics 2024-12-31 Chanju Park , Matteo Favoni , Biagio Lucini , Gert Aarts

In this paper, we introduce a novel methodology for characterising the performance of deep learning networks (ResNets and DenseNet) with respect to training convergence and generalisation as a function of mini-batch size and learning rate…

Computer Vision and Pattern Recognition · Computer Science 2018-10-17 Zhibin Liao , Tom Drummond , Ian Reid , Gustavo Carneiro

The use of mini-batches of data in training artificial neural networks is nowadays very common. Despite its broad usage, theories explaining quantitatively how large or small the optimal mini-batch size should be are missing. This work…

Disordered Systems and Neural Networks · Physics 2024-01-17 Raffaele Marino , Federico Ricci-Tersenghi

A fundamental challenge in Deep Learning is to find optimal step sizes for stochastic gradient descent automatically. In traditional optimization, line searches are a commonly used method to determine step sizes. One problem in Deep…

Machine Learning · Computer Science 2022-02-22 Maximus Mutschler , Kevin Laube , Andreas Zell

The mini-batch stochastic gradient descent (SGD) algorithm is widely used in training machine learning models, in particular deep learning models. We study SGD dynamics under linear regression and two-layer linear networks, with an easy…

Optimization and Control · Mathematics 2020-04-29 Xin Qian , Diego Klabjan

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While for SGD, doubling the batch size can be equivalent to halving the learning rate, the optimal…

Machine Learning · Computer Science 2025-10-17 Alexandru Meterez , Depen Morwani , Jingfeng Wu , Costin-Andrei Oncescu , Cengiz Pehlevan , Sham Kakade

This paper presents a methodology for selecting the mini-batch size that minimizes Stochastic Gradient Descent (SGD) learning time for single and multiple learner problems. By decoupling algorithmic analysis issues from hardware and…

Machine Learning · Computer Science 2019-11-18 Michael P. Perrone , Haidar Khan , Changhoan Kim , Anastasios Kyrillidis , Jerry Quinn , Valentina Salapura

Hessian-free (HF) optimization has been successfully used for training deep autoencoders and recurrent networks. HF uses the conjugate gradient algorithm to construct update directions through curvature-vector products that can be computed…

Machine Learning · Computer Science 2013-05-02 Ryan Kiros

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

We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimize a series of regularized, nonlinearized losses on large…

Machine Learning · Computer Science 2019-03-12 Weiran Wang , Nathan Srebro

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

In deep learning, mini-batch training is commonly used to optimize network parameters. However, the traditional mini-batch method may not learn the under-represented samples and complex patterns in the data, leading to a longer time for…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Subin Sahayam , John Zakkam , Umarani Jayaraman

Modern neural networks are undeniably successful. Numerous works study how the curvature of loss landscapes can affect the quality of solutions. In this work we study the loss landscape by considering the Hessian matrix during network…

Machine Learning · Computer Science 2023-07-25 Lawrence Wang , Stephen Roberts

The goal of this paper is to accelerate the training of machine learning models, a critical challenge since the training of large-scale deep neural models can be computationally expensive. Stochastic gradient descent (SGD) and its variants…

Machine Learning · Computer Science 2025-09-22 Yuen Chen , Yian Wang , Hari Sundaram

Practical results have shown that deep learning optimizers using small constant learning rates, hyperparameters close to one, and large batch sizes can find the model parameters of deep neural networks that minimize the loss functions. We…

Machine Learning · Computer Science 2022-08-23 Hideaki Iiduka

The training process of neural networks is known to be time-consuming, and having a deep architecture only aggravates the issue. This process consists mostly of matrix operations, among which matrix multiplication is the bottleneck. Several…

Machine Learning · Computer Science 2025-06-17 Sana Ebrahimi , Rishi Advani , Abolfazl Asudeh

In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data parallelism seem to differ…

Machine Learning · Computer Science 2018-12-18 Sam McCandlish , Jared Kaplan , Dario Amodei , OpenAI Dota Team