English
Related papers

Related papers: The Future is Log-Gaussian: ResNets and Their Infi…

200 papers

It has been noted in existing literature that over-parameterization in ReLU networks generally improves performance. While there could be several factors involved behind this, we prove some desirable theoretical properties at initialization…

Machine Learning · Statistics 2019-10-03 Devansh Arpit , Yoshua Bengio

This paper presents an investigation of the approximation property of neural networks with unbounded activation functions, such as the rectified linear unit (ReLU), which is the new de-facto standard of deep learning. The ReLU network can…

Neural and Evolutionary Computing · Computer Science 2019-02-27 Sho Sonoda , Noboru Murata

Graph-structured data such as social networks, functional brain networks, gene regulatory networks, communications networks have brought the interest in generalizing deep learning techniques to graph domains. In this paper, we are…

Machine Learning · Computer Science 2018-04-25 Xavier Bresson , Thomas Laurent

Deep neural networks (DNNs) have significantly advanced machine learning, with model depth playing a central role in their successes. The dynamical system modeling approach has recently emerged as a powerful framework, offering new…

Machine Learning · Computer Science 2026-02-25 Jinshu Huang , Mingfei Sun , Chunlin Wu

It is well-known that randomly initialized, push-forward, fully-connected neural networks weakly converge to isotropic Gaussian processes, in the limit where the width of all layers goes to infinity. In this paper, we propose to use the…

Machine Learning · Statistics 2025-05-20 Simmaco Di Lillo , Domenico Marinucci , Michele Salvi , Stefano Vigogna

We study training one-hidden-layer ReLU networks in the neural tangent kernel (NTK) regime, where the networks' biases are initialized to some constant rather than zero. We prove that under such initialization, the neural network will have…

Machine Learning · Computer Science 2024-10-31 Hongru Yang , Ziyu Jiang , Ruizhe Zhang , Yingbin Liang , Zhangyang Wang

Assessing the complexity of functions computed by a neural network helps us understand how the network will learn and generalize. One natural measure of complexity is how the network distorts length - if the network takes a unit-length…

Machine Learning · Statistics 2021-06-24 Boris Hanin , Ryan Jeong , David Rolnick

Noisy network coding, which elegantly combines the conventional compress-and-forward relaying strategy and ideas from network coding, has recently drawn much attention for its simplicity and optimality in achieving to within constant gap of…

Information Theory · Computer Science 2011-12-13 Lei Zhou , Wei Yu

This paper studies the memorization capacity of deep neural networks with ReLU activation. Specifically, we investigate the minimal size of such networks to memorize any $N$ data points in the unit ball with pairwise separation distance…

Machine Learning · Computer Science 2026-03-11 Xin Yang , Yunfei Yang

Gaussian Error Linear Unit (GELU) is a widely used smooth alternative to Rectifier Linear Unit (ReLU), yet many deployment, compression, and analysis toolchains are most naturally expressed for piecewise-linear (ReLU-type) networks. We…

We consider a large class of shallow neural networks with randomly initialized parameters and rectified linear unit activation functions. We prove that these random neural networks are well-defined non-Gaussian processes. As a by-product,…

Machine Learning · Statistics 2025-02-13 Rahul Parhi , Pakshal Bohra , Ayoub El Biari , Mehrsa Pourya , Michael Unser

We study the gradient-based training of large-depth residual networks (ResNets) from standard random initializations. We show that infinite-depth ResNets behave as if they were infinitely wide, regardless of their actual width. More…

Machine Learning · Computer Science 2026-03-04 Lénaïc Chizat

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…

Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the…

Machine Learning · Statistics 2019-05-01 Gang Wang , Georgios B. Giannakis , Jie Chen

A new network with super approximation power is introduced. This network is built with Floor ($\lfloor x\rfloor$) or ReLU ($\max\{0,x\}$) activation function in each neuron and hence we call such networks Floor-ReLU networks. For any…

Machine Learning · Computer Science 2021-03-30 Zuowei Shen , Haizhao Yang , Shijun Zhang

This survey provides an in-depth and explanatory review of the approximation properties of deep neural networks, with a focus on feed-forward and residual architectures. The primary objective is to examine how effectively neural networks…

Machine Learning · Computer Science 2024-12-18 Owen Davis , Mohammad Motamed

Improving the resilience of a network is a fundamental problem in network science, which protects the underlying system from natural disasters and malicious attacks. This is traditionally achieved via successive degree-preserving edge…

Machine Learning · Computer Science 2022-05-24 Shanchao Yang , Kaili Ma , Baoxiang Wang , Tianshu Yu , Hongyuan Zha

The trend towards increasingly deep neural networks has been driven by a general observation that increasing depth increases the performance of a network. Recently, however, evidence has been amassing that simply increasing depth may not be…

Computer Vision and Pattern Recognition · Computer Science 2016-12-01 Zifeng Wu , Chunhua Shen , Anton van den Hengel

We study randomly initialized residual networks using mean field theory and the theory of difference equations. Classical feedforward neural networks, such as those with tanh activations, exhibit exponential behavior on the average when…

Neural and Evolutionary Computing · Computer Science 2017-12-27 Greg Yang , Samuel S. Schoenholz

Recovering images from undersampled linear measurements typically leads to an ill-posed linear inverse problem, that asks for proper statistical priors. Building effective priors is however challenged by the low train and test overhead…

Artificial Intelligence · Computer Science 2017-11-29 Morteza Mardani , Hatef Monajemi , Vardan Papyan , Shreyas Vasanawala , David Donoho , John Pauly