English
Related papers

Related papers: Large-width asymptotics for ReLU neural networks w…

200 papers

The expressive power of neural networks is important for understanding deep learning. Most existing works consider this problem from the view of the depth of a network. In this paper, we study how width affects the expressiveness of neural…

Machine Learning · Computer Science 2017-11-02 Zhou Lu , Hongming Pu , Feicheng Wang , Zhiqiang Hu , Liwei Wang

Activation functions critically influence trainability and expressivity, and recent work has therefore explored a broad range of nonlinearities. However, widely used Gaussian i.i.d. initializations are designed to preserve activation…

Machine Learning · Computer Science 2025-12-17 Hyunwoo Lee , Hayoung Choi , Hyunju Kim

Neural Networks (NNs) are the method of choice for building learning algorithms. Their popularity stems from their empirical success on several challenging learning problems. However, most scholars agree that a convincing theoretical…

Numerical Analysis · Mathematics 2021-01-01 Ronald DeVore , Boris Hanin , Guergana Petrova

The ability of neural networks to provide `best in class' approximation across a wide range of applications is well-documented. Nevertheless, the powerful expressivity of neural networks comes to naught if one is unable to effectively train…

Machine Learning · Computer Science 2020-07-15 Mark Ainsworth , Yeonjong Shin

Recurrent neural networks are powerful models for sequential data, able to represent complex dependencies in the sequence that simpler models such as hidden Markov models cannot handle. Yet they are notoriously hard to train. Here we…

Neural and Evolutionary Computing · Computer Science 2015-02-04 Yann Ollivier

Recurrent neural networks (RNNs) have been widely used for processing sequential data. However, RNNs are commonly difficult to train due to the well-known gradient vanishing and exploding problems and hard to learn long-term patterns. Long…

Computer Vision and Pattern Recognition · Computer Science 2019-10-15 Shuai Li , Wanqing Li , Chris Cook , Ce Zhu , Yanbo Gao

The training of artificial neural networks (ANNs) is nowadays a highly relevant algorithmic procedure with many applications in science and industry. Roughly speaking, ANNs can be regarded as iterated compositions between affine linear…

Optimization and Control · Mathematics 2022-07-14 Simon Eberle , Arnulf Jentzen , Adrian Riekert , Georg Weiss

The design of modern neural architectures has converged through incremental empirical choices, yet the mechanisms governing their training dynamics remain only partially understood. We identify and analyze a negative weight drift induced by…

Machine Learning · Computer Science 2026-05-22 Egor Shvetsov , Aleksandr Serkov , Shokorov Viacheslav , Redko Dmitry , Vladislav Goloshchapov , Evgeny Burnaev

Despite remarkable performance on a variety of tasks, many properties of deep neural networks are not yet theoretically understood. One such mystery is the depth degeneracy phenomenon: the deeper you make your network, the closer your…

Machine Learning · Statistics 2025-11-18 Cameron Jakub , Mihai Nica

A recent breakthrough in deep learning theory shows that the training of over-parameterized deep neural networks can be characterized by a kernel function called \textit{neural tangent kernel} (NTK). However, it is known that this type of…

Machine Learning · Computer Science 2020-10-07 Zixiang Chen , Yuan Cao , Quanquan Gu , Tong Zhang

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

Machine Learning · Computer Science 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

Larger and deeper networks generalise well despite their increased capacity to overfit. Understanding why this happens is theoretically and practically important. One recent approach looks at the infinitely wide limits of such networks and…

Machine Learning · Computer Science 2023-10-13 Adrian Goldwaser , Hong Ge

The Neural Tangent Kernel (NTK) has discovered connections between deep neural networks and kernel methods with insights of optimization and generalization. Motivated by this, recent works report that NTK can achieve better performances…

Machine Learning · Computer Science 2021-04-06 Insu Han , Haim Avron , Neta Shoham , Chaewon Kim , Jinwoo Shin

How neural network behaves during the training over different choices of hyperparameters is an important question in the study of neural networks. In this work, inspired by the phase diagram in statistical mechanics, we draw the phase…

Machine Learning · Computer Science 2020-10-14 Tao Luo , Zhi-Qin John Xu , Zheng Ma , Yaoyu Zhang

The intermediate layers of deep networks can be characterised as a Gaussian process, in particular the Edge-of-Chaos (EoC) initialisation strategy prescribes the limiting covariance matrix of the Gaussian process. Here we show that the…

Machine Learning · Computer Science 2026-02-06 Emily Dent , Jared Tanner

Understanding the properties of neural networks trained via stochastic gradient descent (SGD) is at the heart of the theory of deep learning. In this work, we take a mean-field view, and consider a two-layer ReLU network trained via SGD for…

Machine Learning · Computer Science 2022-05-02 Alexander Shevchenko , Vyacheslav Kungurtsev , Marco Mondelli

The overparameterization of variational quantum circuits, as a model of Quantum Neural Networks (QNN), not only improves their trainability but also serves as a method for evaluating the property of a given ansatz by investigating their…

Quantum Physics · Physics 2023-05-23 Ali Rad

Understanding the asymptotic behavior of wide networks is of considerable interest. In this work, we present a general method for analyzing this large width behavior. The method is an adaptation of Feynman diagrams, a standard tool for…

Machine Learning · Computer Science 2019-09-26 Ethan Dyer , Guy Gur-Ari

In training a neural network with gradient descent (GD), each iteration induces a linear operator that governs first-order updates to a model's internal state variables. We define this operator as the Global Empirical Neural Tangent Kernel…

Machine Learning · Computer Science 2026-05-12 James Hazelden , Laura Driscoll , Eli Shlizerman , Eric Shea-Brown

We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, nondifferentiable, bounded functions with additive noise when trained by Gradient Descent (GD). To avoid the problem that in the presence of noise,…

Machine Learning · Computer Science 2023-04-07 Ilja Kuzborskij , Csaba Szepesvári