中文
相关论文

相关论文: Normalization effects on shallow neural networks a…

200 篇论文

We study the effect of normalization on the layers of deep neural networks of feed-forward type. A given layer $i$ with $N_{i}$ hidden units is allowed to be normalized by $1/N_{i}^{\gamma_{i}}$ with $\gamma_{i}\in[1/2,1]$ and we study the…

机器学习 · 计算机科学 2022-09-05 Jiahui Yu , Konstantinos Spiliopoulos

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

机器学习 · 计算机科学 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

In this work, we study the training and generalization performance of two-layer neural networks (NNs) after one gradient descent step under structured data modeled by Gaussian mixtures. While previous research has extensively analyzed this…

机器学习 · 统计学 2025-05-20 Samet Demir , Zafer Dogan

We consider gradient-based optimisation of wide, shallow neural networks, where the output of each hidden node is scaled by a positive parameter. The scaling parameters are non-identical, differing from the classical Neural Tangent Kernel…

机器学习 · 统计学 2025-02-19 Francois Caron , Fadhel Ayed , Paul Jung , Hoil Lee , Juho Lee , Hongseok Yang

We analyze multi-layer neural networks in the asymptotic regime of simultaneously (A) large network sizes and (B) large numbers of stochastic gradient descent training iterations. We rigorously establish the limiting behavior of the…

概率论 · 数学 2021-04-06 Justin Sirignano , Konstantinos Spiliopoulos

We study the relationship between the frequency of a function and the speed at which a neural network learns it. We build on recent results that show that the dynamics of overparameterized neural networks trained with gradient descent can…

机器学习 · 计算机科学 2019-12-03 Ronen Basri , David Jacobs , Yoni Kasten , Shira Kritchman

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

机器学习 · 计算机科学 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

Neural networks are known to develop latent representations that are $aligned$, namely structurally similar across networks trained with different architectures, training protocols, or training datasets. We study this phenomenon in a…

机器学习 · 统计学 2026-05-27 Ali Hussaini Umar , Alessandro Laio

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…

机器学习 · 计算机科学 2024-10-11 Semih Cayci , Atilla Eryilmaz

Although overparameterized models have achieved remarkable practical success, their theoretical properties, particularly their generalization behavior, remain incompletely understood. The well known double descents phenomenon suggests that…

机器学习 · 统计学 2026-01-06 Haoran Zhan , Yingcun Xia

Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the…

机器学习 · 统计学 2016-07-22 Jimmy Lei Ba , Jamie Ryan Kiros , Geoffrey E. Hinton

On a variety of tasks, the performance of neural networks predictably improves with training time, dataset size and model size across many orders of magnitude. This phenomenon is known as a neural scaling law. Of fundamental importance is…

机器学习 · 统计学 2024-06-25 Blake Bordelon , Alexander Atanasov , Cengiz Pehlevan

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

机器学习 · 计算机科学 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

Recent theoretical works have characterized the dynamics of wide shallow neural networks trained via gradient descent in an asymptotic mean-field limit when the width tends towards infinity. At initialization, the random sampling of the…

概率论 · 数学 2022-03-29 Zhengdao Chen , Grant M. Rotskoff , Joan Bruna , Eric Vanden-Eijnden

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

机器学习 · 计算机科学 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

We analyze single-layer neural networks with the Xavier initialization in the asymptotic regime of large numbers of hidden units and large numbers of stochastic gradient descent training steps. The evolution of the neural network during…

概率论 · 数学 2022-04-13 Justin Sirignano , Konstantinos Spiliopoulos

Training neural networks is an optimization problem, and finding a decent set of parameters through gradient descent can be a difficult task. A host of techniques has been developed to aid this process before and during the training phase.…

机器学习 · 计算机科学 2020-08-19 Divya Gaur , Joachim Folz , Andreas Dengel

We investigate the generalization and optimization properties of shallow neural-network classifiers trained by gradient descent in the interpolating regime. Specifically, in a realizable scenario where model weights can achieve arbitrarily…

机器学习 · 统计学 2023-03-29 Hossein Taheri , Christos Thrampoulidis

Machine learning, and in particular neural network models, have revolutionized fields such as image, text, and speech recognition. Today, many important real-world applications in these areas are driven by neural networks. There are also…

概率论 · 数学 2019-11-12 Justin Sirignano , Konstantinos Spiliopoulos

Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the dynamics of stochastic gradient descent over diagonal linear…

机器学习 · 计算机科学 2021-12-08 Scott Pesme , Loucas Pillaud-Vivien , Nicolas Flammarion
‹ 上一页 1 2 3 10 下一页 ›