English
Related papers

Related papers: Wide neural networks with general weights: converg…

200 papers

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of the favorable properties of Gaussian processes, this…

Machine Learning · Computer Science 2026-03-24 Steven Adams , Andrea Patanè , Morteza Lahijanian , Luca Laurenti

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…

We give a proof that, under relatively mild conditions, fully-connected feed-forward deep random neural networks converge to a Gaussian mixture distribution as only the width of the last hidden layer goes to infinity. We conducted…

Machine Learning · Statistics 2022-04-27 Yasuhiko Asao , Ryotaro Sakamoto , Shiro Takagi

By the continuous mapping theorem, if a sequence of $d$-dimensional random vectors $(\mathbf{W}_n)_{n\geq1}$ converges in distribution to a multivariate normal random variable $\Sigma^{1/2}\mathbf{Z}$, then the sequence of random variables…

Probability · Mathematics 2020-03-18 Robert E. Gaunt

Finite-width fully connected neural networks with Gaussian-initialized weights deviate from their infinite-width Gaussian limit, exhibiting non-vanishing higher-order cumulants. We approximate these deviations, for a neural network…

Machine Learning · Statistics 2026-05-26 Lucia Celli

We consider fully connected feed-forward deep neural networks (NNs) where weights and biases are independent and identically distributed as symmetric centered stable distributions. Then, we show that the infinite wide limit of the NN, under…

Machine Learning · Statistics 2020-03-03 Stefano Favaro , Sandra Fortini , Stefano Peluchetti

Many convolutional neural networks (CNNs) have a feed-forward structure. In this paper, a linear program that estimates the Lipschitz bound of such CNNs is proposed. Several CNNs, including the scattering networks, the AlexNet and the…

Information Theory · Computer Science 2018-08-07 Dongmian Zou , Radu Balan , Maneesh Singh

Quantitative convergence in Wasserstein distance is often easier to establish than that in total variation distance. We show that such bounds allowing subgeometric rates yield central limit theorems (CLTs) for additive functionals of Markov…

Statistics Theory · Mathematics 2025-11-25 Rui Jin , Aixin Tan

This paper provides a general framework for Stein's density method for multivariate continuous distributions. The approach associates to any probability density function a canonical operator and Stein class, as well as an infinite…

Probability · Mathematics 2023-04-27 Guillaume Mijoule , Martin Raič , Gesine Reinert , Yvik Swan

Deep neural networks (DNNs) exhibit an exceptional capacity for generalization in practical applications. This work aims to capture the effect and benefits of depth for supervised learning via information-theoretic generalization bounds. We…

Machine Learning · Computer Science 2025-05-09 Haiyun He , Ziv Goldfeld

In this paper, we study the quantitative convergence of shallow neural networks trained via gradient descent to their associated Gaussian processes in the infinite-width limit. While previous work has established qualitative convergence…

Machine Learning · Statistics 2026-03-06 Eloy Mosig , Andrea Agazzi , Dario Trevisan

This paper investigates the approximation power of three types of random neural networks: (a) infinite width networks, with weights following an arbitrary distribution; (b) finite width networks obtained by subsampling the preceding…

Machine Learning · Computer Science 2019-10-21 Bolton Bailey , Ziwei Ji , Matus Telgarsky , Ruicheng Xian

Ensembles of neural network weight matrices are studied through the training process for the MNIST classification problem, testing the efficacy of matrix models for representing their distributions, under assumptions of Gaussianity and…

Machine Learning · Computer Science 2025-10-08 Edward Hirst , Sanjaye Ramgoolam

Several recent trends in machine learning theory and practice, from the design of state-of-the-art Gaussian Process to the convergence analysis of deep neural nets (DNNs) under stochastic gradient descent (SGD), have found it fruitful to…

Neural and Evolutionary Computing · Computer Science 2020-04-07 Greg Yang

This paper introduces a new parameterization of deep neural networks (both fully-connected and convolutional) with guaranteed $\ell^2$ Lipschitz bounds, i.e. limited sensitivity to input perturbations. The Lipschitz guarantees are…

Machine Learning · Computer Science 2023-06-07 Ruigang Wang , Ian R. Manchester

Overparameterized neural networks often show a benign overfitting property in the sense of achieving excellent generalization behavior despite the number of parameters exceeding the number of training examples. A promising direction to…

Machine Learning · Computer Science 2026-04-23 Yunwen Lei , Yufeng Xie

In a recent work arXiv:2008.08601, Halverson, Maiti and Stoner proposed a description of neural networks in terms of a Wilsonian effective field theory. The infinite-width limit is mapped to a free field theory, while finite $N$ corrections…

High Energy Physics - Theory · Physics 2022-03-01 Harold Erbin , Vincent Lahoche , Dine Ousmane Samary

The proper initialization of weights is crucial for the effective training and fast convergence of deep neural networks (DNNs). Prior work in this area has mostly focused on balancing the variance among weights per layer to maintain…

Machine Learning · Computer Science 2020-06-05 Maciej Skorski , Alessandro Temperoni , Martin Theobald

It has been recently observed in much of the literature that neural networks exhibit a bottleneck rank property: for larger depths, the activation and weights of neural networks trained with gradient-based methods tend to be of…

Machine Learning · Computer Science 2025-11-26 Antoine Ledent , Rodrigo Alves , Yunwen Lei