中文
相关论文

相关论文: Scaling Limits of Wide Neural Networks with Weight…

200 篇论文

A recent line of works studied wide deep neural networks (DNNs) by approximating them as Gaussian Processes (GPs). A DNN trained with gradient flow was shown to map to a GP governed by the Neural Tangent Kernel (NTK), whereas earlier works…

机器学习 · 统计学 2021-12-15 Gadi Naveh , Oded Ben-David , Haim Sompolinsky , Zohar Ringel

Wide neural networks with random weights and biases are Gaussian processes, as originally observed by Neal (1995) and more recently by Lee et al. (2018) and Matthews et al. (2018) for deep fully-connected networks, as well as by Novak et…

神经与进化计算 · 计算机科学 2021-05-11 Greg Yang

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we…

This paper presents a comprehensive study on the convergence rates of the stochastic gradient descent (SGD) algorithm when applied to overparameterized two-layer neural networks. Our approach combines the Neural Tangent Kernel (NTK)…

机器学习 · 统计学 2024-07-11 Dinghao Cao , Zheng-Chu Guo , Lei Shi

In the last decade, deep learning has become a major component of artificial intelligence. The workhorse of deep learning is the optimization of loss functions by stochastic gradient descent (SGD). Traditionally in deep learning, neural…

机器学习 · 计算机科学 2021-04-27 Benjamin Scellier

Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties. In this paper, we study the relationship between random, wide, fully connected, feedforward…

Recent works have examined theoretical and empirical properties of wide neural networks trained in the Neural Tangent Kernel (NTK) regime. Given that biological neural networks are much wider than their artificial counterparts, we consider…

机器学习 · 计算机科学 2022-07-14 Akhilan Boopathy , Ila Fiete

Neural networks with wide layers have attracted significant attention due to their equivalence to Gaussian processes, enabling perfect fitting of training data while maintaining generalization performance, known as benign overfitting.…

机器学习 · 计算机科学 2023-10-18 Tianxiang Gao , Xiaokai Huo , Hailiang Liu , Hongyang Gao

Deep neural networks (NNs) encounter scalability limitations when confronted with a vast array of neurons, thereby constraining their achievable network depth. To address this challenge, we propose an integration of tensor networks (TN)…

无序系统与神经网络 · 物理学 2024-08-20 Saeed S. Jahromi , Roman Orus

Neural networks, a central tool in machine learning, have demonstrated remarkable, high fidelity performance on image recognition and classification tasks. These successes evince an ability to accurately represent high dimensional…

机器学习 · 统计学 2023-02-08 Grant M. Rotskoff , Eric Vanden-Eijnden

We study the convergence of gradient descent (GD) and stochastic gradient descent (SGD) for training $L$-hidden-layer linear residual networks (ResNets). We prove that for training deep residual networks with certain linear transformations…

机器学习 · 计算机科学 2020-03-03 Difan Zou , Philip M. Long , Quanquan Gu

Generalization error bounds for deep neural networks trained by stochastic gradient descent (SGD) are derived by combining a dynamical control of an appropriate parameter norm and the Rademacher complexity estimate based on parameter norms.…

机器学习 · 计算机科学 2023-05-30 Mingze Wang , Chao Ma

Understanding deep neural networks (DNNs) is a key challenge in the theory of machine learning, with potential applications to the many fields where DNNs have been successfully used. This article presents a scaling limit for a DNN being…

统计理论 · 数学 2019-06-04 Dyego Araújo , Roberto I. Oliveira , Daniel Yukimura

Analyzing neural network dynamics via stochastic gradient descent (SGD) is crucial to building theoretical foundations for deep learning. Previous work has analyzed structured inputs within the \textit{hidden manifold model}, often under…

机器学习 · 统计学 2025-12-01 Jaeyong Bae , Hawoong Jeong

Deep Gaussian Process (DGP) as a model prior in Bayesian learning intuitively exploits the expressive power in function composition. DGPs also offer diverse modeling capabilities, but inference is challenging because marginalization in…

机器学习 · 计算机科学 2022-08-02 Chi-Ken Lu , Patrick Shafto

This article studies the infinite-width limit of deep feedforward neural networks whose weights are dependent, and modelled via a mixture of Gaussian distributions. Each hidden node of the network is assigned a nonnegative random variable…

机器学习 · 统计学 2025-02-06 Hoil Lee , Fadhel Ayed , Paul Jung , Juho Lee , Hongseok Yang , François Caron

The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the \emph{classical} central limit theorem (CLT) kicks in. This assumption is often made…

机器学习 · 统计学 2019-12-03 Umut Şimşekli , Mert Gürbüzbalaban , Thanh Huy Nguyen , Gaël Richard , Levent Sagun

In this paper, we study the data-dependent convergence and generalization behavior of gradient methods for neural networks with smooth activation. Our first result is a novel bound on the excess risk of deep networks trained by the logistic…

机器学习 · 计算机科学 2024-12-09 Hossein Taheri , Christos Thrampoulidis , Arya Mazumdar

We prove that a randomly initialized neural network of *any architecture* has its Tangent Kernel (NTK) converge to a deterministic limit, as the network widths tend to infinity. We demonstrate how to calculate this limit. In prior…

机器学习 · 统计学 2020-12-01 Greg Yang

In a recently published paper [1], it is shown that deep neural networks (DNNs) with random Gaussian weights preserve the metric structure of the data, with the property that the distance shrinks more when the angle between the two data…

机器学习 · 统计学 2019-04-02 Talha Cihad Gulcu , Alper Gungor
‹ 上一页 1 2 3 10 下一页 ›