English
Related papers

Related papers: Infinitely wide limits for deep Stable neural netw…

200 papers

We show that taking the width and depth to infinity in a deep neural network with skip connections, when branches are scaled by $1/\sqrt{depth}$ (the only nontrivial scaling), result in the same covariance structure no matter how that limit…

Machine Learning · Statistics 2023-08-11 Soufiane Hayou , Greg Yang

Deep linear networks have been extensively studied, as they provide simplified models of deep learning. However, little is known in the case of finite-width architectures with multiple outputs and convolutional layers. In this manuscript,…

Machine Learning · Statistics 2025-06-26 Federico Bassetti , Marco Gherardi , Alessandro Ingrosso , Mauro Pastore , Pietro Rotondo

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…

Machine Learning · Statistics 2019-04-02 Talha Cihad Gulcu , Alper Gungor

The correlation length-scale next to the noise variance are the most used hyperparameters for the Gaussian processes. Typically, stationary covariance functions are used, which are only dependent on the distances between input points and…

Machine Learning · Computer Science 2017-10-30 Kevin Cremanns , Dirk Roos

This article contributes to the current statistical theory of deep neural networks (DNNs). It was shown that DNNs are able to circumvent the so--called curse of dimensionality in case that suitable restrictions on the structure of the…

Statistics Theory · Mathematics 2020-10-14 Sophie Langer

Achieving transparency in black-box deep learning algorithms is still an open challenge. High dimensional features and decisions given by deep neural networks (NN) require new algorithms and methods to expose its mechanisms. Current…

Machine Learning · Computer Science 2020-06-12 Schyler C. Sun , Chen Li , Zhuangkun Wei , Antonios Tsourdos , Weisi Guo

Skewness and non-Gaussian behavior are essential features of the distribution of short-scale velocity increments in isotropic turbulent flows. Yet, although the skewness has been generally linked to time-reversal symmetry breaking and…

Neural Tangent Kernel (NTK) theory is widely used to study the dynamics of infinitely-wide deep neural networks (DNNs) under gradient descent. But do the results for infinitely-wide networks give us hints about the behavior of real…

Machine Learning · Computer Science 2022-02-02 Mariia Seleznova , Gitta Kutyniok

We analyze the joint probability distribution on the lengths of the vectors of hidden variables in different layers of a fully connected deep network, when the weights and biases are chosen randomly according to Gaussian distributions, and…

Machine Learning · Computer Science 2019-01-09 Philip M. Long , Hanie Sedghi

The logit outputs of a feedforward neural network at initialization are conditionally Gaussian, given a random covariance matrix defined by the penultimate layer. In this work, we study the distribution of this random matrix. Recent work…

Machine Learning · Statistics 2023-06-16 Mufan Bill Li , Mihai Nica , Daniel M. Roy

Characterizing how neural network depth, width, and dataset size jointly impact model quality is a central problem in deep learning theory. We give here a complete solution in the special case of linear networks with output dimension one…

Machine Learning · Statistics 2023-05-16 Boris Hanin , Alexander Zlokapa

We prove large and moderate deviations for the output of Gaussian fully connected neural networks. The main achievements concern deep neural networks (i.e., when the model has more than one hidden layer) and hold for bounded and continuous…

Probability · Mathematics 2026-04-01 Claudio Macci , Barbara Pacchiarotti , Giovanni Luca Torrisi

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.…

Machine Learning · Computer Science 2023-10-18 Tianxiang Gao , Xiaokai Huo , Hailiang Liu , Hongyang Gao

Normalizing flows are a flexible class of probability distributions, expressed as transformations of a simple base distribution. A limitation of standard normalizing flows is representing distributions with heavy tails, which arise in…

Machine Learning · Statistics 2025-06-13 Tennessee Hickling , Dennis Prangle

Power-law probability distributions are widely used to model extreme statistical events in complex systems, with applications to a vast array of natural phenomena ranging from earthquakes to stock market crashes to pandemics. We show that…

Quantum Physics · Physics 2026-04-08 Wai-Keong Mok

This paper studies large deviation principles and weak convergence, both at the level of finite-dimensional distributions and in functional form, for a class of continuous, isotropic, centered Gaussian random fields defined on the unit…

Probability · Mathematics 2026-01-09 Simmaco Di Lillo , Claudio Macci , Barbara Pacchiarotti

There has recently been much work on the "wide limit" of neural networks, where Bayesian neural networks (BNNs) are shown to converge to a Gaussian process (GP) as all hidden layers are sent to infinite width. However, these results do not…

Machine Learning · Statistics 2020-07-07 Devanshu Agrawal , Theodore Papamarkou , Jacob Hinkle

Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have shown superior performance on real-world datasets. Despite their…

Machine Learning · Computer Science 2019-05-15 Saurabh Verma , Zhi-Li Zhang

We derive exact upper and lower bounds for the cumulative distribution function (cdf) of the output of a neural network (NN) over its entire support subject to noisy (stochastic) inputs. The upper and lower bounds converge to the true cdf…

Machine Learning · Computer Science 2025-06-11 Andrey Kofnov , Daniel Kapla , Ezio Bartocci , Efstathia Bura

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