English
Related papers

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

200 papers

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…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

In a neural network with ReLU activations, the number of piecewise linear regions in the output can grow exponentially with depth. However, this is highly unlikely to happen when the initial parameters are sampled randomly, which therefore…

Machine Learning · Computer Science 2025-10-17 Max Milkert , David Hyde , Forrest Laine

It has long been known that a single-layer fully-connected neural network with an i.i.d. prior over its parameters is equivalent to a Gaussian process (GP), in the limit of infinite network width. This correspondence enables exact Bayesian…

A Bayesian treatment can mitigate overconfidence in ReLU nets around the training data. But far away from them, ReLU Bayesian neural networks (BNNs) can still underestimate uncertainty and thus be asymptotically overconfident. This issue…

Machine Learning · Computer Science 2022-01-25 Agustinus Kristiadi , Matthias Hein , Philipp Hennig

We analyze the universal approximation constraints of narrow Residual Neural Networks (ResNets) both theoretically and numerically. For deep neural networks without input space augmentation, a central constraint is the inability to…

Dynamical Systems · Mathematics 2026-03-31 Christian Kuehn , Sara-Viola Kuntz , Tobias Wöhrer

There is a recent and growing literature on large-width asymptotic properties of Gaussian neural networks (NNs), namely NNs whose weights are initialized as Gaussian distributions. Two popular problems are: i) the study of the large-width…

Machine Learning · Computer Science 2023-01-05 Stefano Favaro , Sandra Fortini , Stefano Peluchetti

Two networks are equivalent if they produce the same output for any given input. In this paper, we study the possibility of transforming a deep neural network to another network with a different number of units or layers, which can be…

Machine Learning · Computer Science 2019-05-29 Abhinav Kumar , Thiago Serra , Srikumar Ramalingam

In this work, we consider the approximation of a large class of bounded functions, with minimal regularity assumptions, by ReLU neural networks. We show that the approximation error can be bounded from above by a quantity proportional to…

Machine Learning · Statistics 2026-02-27 Owen Davis , Gianluca Geraci , Mohammad Motamed

We consider an existing conjecture addressing the asymptotic behavior of neural networks in the large width limit. The results that follow from this conjecture include tight bounds on the behavior of wide networks during stochastic gradient…

Machine Learning · Computer Science 2020-06-15 Kyle Aitken , Guy Gur-Ari

Graph neural networks (GNNs) have shown superiority in many prediction tasks over graphs due to their impressive capability of capturing nonlinear relations in graph-structured data. However, for node classification tasks, often, only…

Machine Learning · Computer Science 2022-10-21 Rongzhe Wei , Haoteng Yin , Junteng Jia , Austin R. Benson , Pan Li

This article derives and validates three principles for initialization and architecture selection in finite width graph neural networks (GNNs) with ReLU activations. First, we theoretically derive what is essentially the unique…

Machine Learning · Statistics 2023-06-21 Gage DeZoort , Boris Hanin

This paper investigates the relationship between the universal approximation property of deep neural networks and topological characteristics of datasets. Our primary contribution is to introduce data topology-dependent upper bounds on the…

Machine Learning · Computer Science 2023-05-29 Sangmin Lee , Jong Chul Ye

Augmenting neural networks with skip connections, as introduced in the so-called ResNet architecture, surprised the community by enabling the training of networks of more than 1,000 layers with significant performance gains. This paper…

Computer Vision and Pattern Recognition · Computer Science 2020-04-24 Alireza Zaeemzadeh , Nazanin Rahnavard , Mubarak Shah

This paper studies the approximation capacity of ReLU neural networks with norm constraint on the weights. We prove upper and lower bounds on the approximation error of these networks for smooth function classes. The lower bound is derived…

Machine Learning · Computer Science 2023-03-31 Yuling Jiao , Yang Wang , Yunfei Yang

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the success of SGD for…

Machine Learning · Statistics 2020-06-15 Yiping Lu , Chao Ma , Yulong Lu , Jianfeng Lu , Lexing Ying

Inference in deep Bayesian neural networks is only fully understood in the infinite-width limit, where the posterior flexibility afforded by increased depth washes out and the posterior predictive collapses to a shallow Gaussian process.…

Machine Learning · Computer Science 2022-05-03 Jacob A. Zavatone-Veth , Cengiz Pehlevan

Study of neural networks with infinite width is important for better understanding of the neural network in practical application. In this work, we derive the equivalence of the deep, infinite-width maxout network and the Gaussian process…

Machine Learning · Statistics 2022-08-29 Libin Liang , Ye Tian , Ge Cheng

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for…

Machine Learning · Computer Science 2018-12-31 Difan Zou , Yuan Cao , Dongruo Zhou , Quanquan Gu

In this paper we provide explicit upper bounds on some distances between the (law of the) output of a random Gaussian NN and (the law of) a random Gaussian vector. Our results concern both shallow random Gaussian neural networks with…

Recent analyses of neural networks with shaped activations (i.e. the activation function is scaled as the network size grows) have led to scaling limits described by differential equations. However, these results do not a priori tell us…

Machine Learning · Statistics 2024-04-22 Mufan Bill Li , Mihai Nica