English
Related papers

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

200 papers

In the context of the optimization of Deep Neural Networks, we propose to rescale the learning rate using a new technique of automatic differentiation. This technique relies on the computation of the {\em curvature}, a second order…

Neural and Evolutionary Computing · Computer Science 2022-10-27 Frédéric de Gournay , Alban Gossard

We systematically analyze optimization dynamics in deep neural networks (DNNs) trained with stochastic gradient descent (SGD) and study the effect of learning rate $\eta$, depth $d$, and width $w$ of the neural network. By analyzing the…

Machine Learning · Computer Science 2023-10-25 Dayal Singh Kalra , Maissam Barkeshli

Many modern learning tasks involve fitting nonlinear models to data which are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Due to this overparameterization, the training…

Machine Learning · Computer Science 2018-12-27 Samet Oymak , Mahdi Soltanolkotabi

Large-batch training is an efficient approach for current distributed deep learning systems. It has enabled researchers to reduce the ImageNet/ResNet-50 training from 29 hours to around 1 minute. In this paper, we focus on studying the…

Machine Learning · Computer Science 2020-06-16 Yang You , Yuhui Wang , Huan Zhang , Zhao Zhang , James Demmel , Cho-Jui Hsieh

We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learning architecture on a fine-grained-level. Individual…

Machine Learning · Computer Science 2020-04-06 Babak Ehteshami Bejnordi , Tijmen Blankevoort , Max Welling

The learning rate in stochastic gradient methods is a critical hyperparameter that is notoriously costly to tune via standard grid search, especially for training modern large-scale models with billions of parameters. We identify a…

Machine Learning · Computer Science 2026-02-17 Amit Attia , Tomer Koren

Quadratic approximations form a fundamental building block of machine learning methods. E.g., second-order optimizers try to find the Newton step into the minimum of a local quadratic proxy to the objective function; and the second-order…

Machine Learning · Computer Science 2025-01-29 Lukas Tatzel , Bálint Mucsányi , Osane Hackel , Philipp Hennig

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

In this work, we investigate the dynamics of stochastic gradient descent (SGD) when training a single-neuron autoencoder with linear or ReLU activation on orthogonal data. We show that for this non-convex problem, randomly initialized SGD…

Machine Learning · Statistics 2023-08-08 Nikhil Ghosh , Spencer Frei , Wooseok Ha , Bin Yu

Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today. We introduce a mini-batch selection strategy based on submodular function maximization. Our novel submodular formulation…

Machine Learning · Computer Science 2019-06-21 K J Joseph , Vamshi Teja R , Krishnakant Singh , Vineeth N Balasubramanian

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

This paper deals with nonconvex stochastic optimization problems in deep learning and provides appropriate learning rates with which adaptive learning rate optimization algorithms, such as Adam and AMSGrad, can approximate a stationary…

Optimization and Control · Mathematics 2020-11-24 Hideaki Iiduka

We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a…

Machine Learning · Computer Science 2024-10-22 Tomer Galanti , Zachary S. Siegel , Aparna Gupte , Tomaso Poggio

Deep neural networks are commonly trained using stochastic non-convex optimization procedures, which are driven by gradient information estimated on fractions (batches) of the dataset. While it is commonly accepted that batch size is an…

Machine Learning · Computer Science 2016-04-26 Ilya Loshchilov , Frank Hutter

Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform…

Machine Learning · Computer Science 2020-12-03 Guy Hacohen , Daphna Weinshall

We study feature learning in two-layer neural networks within the linear-width regime, where the number of hidden neurons, sample size, and input dimension scale proportionally. While recent work has analyzed feature learning via a single…

Machine Learning · Statistics 2026-05-25 Behrad Moniri , Hamed Hassani

Large-batch training has been essential in leveraging large-scale datasets and models in deep learning. While it is computationally beneficial to use large batch sizes, it often requires a specially designed learning rate (LR) schedule to…

Machine Learning · Computer Science 2021-07-14 Chiheon Kim , Saehoon Kim , Jongmin Kim , Donghoon Lee , Sungwoong Kim

Parameter reduction has been an important topic in deep learning due to the ever-increasing size of deep neural network models and the need to train and run them on resource limited machines. Despite many efforts in this area, there were no…

Machine Learning · Computer Science 2019-02-26 Yibo Lin , Zhao Song , Lin F. Yang

Stochastic Gradient Descent (SGD) and its variants are almost universally used to train neural networks and to fit a variety of other parametric models. An important hyperparameter in this context is the batch size, which determines how…

Optimization and Control · Mathematics 2023-12-05 Stefan Perko

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
‹ Prev 1 3 4 5 6 7 10 Next ›