English
Related papers

Related papers: Non-Vacuous Generalisation Bounds for Shallow Neur…

200 papers

A new non-linear variant of a quantitative extension of the uniform boundedness principle is used to show sharpness of error bounds for univariate approximation by sums of sigmoid and ReLU functions. Single hidden layer feedforward neural…

Functional Analysis · Mathematics 2020-06-18 Steffen Goebbels

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…

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

Application of deep neural networks to medical imaging tasks has in some sense become commonplace. Still, a "thorn in the side" of the deep learning movement is the argument that deep networks are prone to overfitting and are thus unable to…

Machine Learning · Computer Science 2021-07-12 Anthony Sicilia , Xingchen Zhao , Anastasia Sosnovskikh , Seong Jae Hwang

In many research fields in artificial intelligence, it has been shown that deep neural networks are useful to estimate unknown functions on high dimensional input spaces. However, their generalization performance is not yet completely…

Machine Learning · Computer Science 2023-04-21 Shuya Nagayasu , Sumio Watanabe

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 the emerging paradigm of edge learning, neural networks (NNs) are partitioned across distributed edge devices that collaboratively perform inference via wireless transmission. However, deploying NNs for edge inference over wireless…

Information Theory · Computer Science 2026-05-08 Yangshuo He , Guanding Yu , Jingge Zhu

Implicit neural networks have become increasingly attractive in the machine learning community since they can achieve competitive performance but use much less computational resources. Recently, a line of theoretical works established the…

Machine Learning · Computer Science 2022-10-03 Tianxiang Gao , Hongyang Gao

We investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities. Bayesian neural networks with Gaussian priors are well known to induce an L2, "weight decay", regularization. Our results…

Machine Learning · Statistics 2019-05-13 Mariia Vladimirova , Jakob Verbeek , Pablo Mesejo , Julyan Arbel

We derive generalization error bounds for the training of two-layer neural networks without assuming boundedness of the loss function, using Wasserstein distance estimates on the discrepancy between a probability distribution and its…

Machine Learning · Statistics 2026-04-09 Jiang Yu Nguwi , Nicolas Privault

Large width limits have been a recent focus of deep learning research: modulo computational practicalities, do wider networks outperform narrower ones? Answering this question has been challenging, as conventional networks gain…

Machine Learning · Computer Science 2021-11-09 Geoff Pleiss , John P. Cunningham

We study the Finite-Dimensional Distributions (FDDs) of deep neural networks with randomly initialized weights that have finite-order moments. Specifically, we establish Gaussian approximation bounds in the Wasserstein-$1$ norm between the…

Machine Learning · Statistics 2026-03-05 Krishnakumar Balasubramanian , Nathan Ross

Classical neural networks with random initialization famously behave as Gaussian processes in the limit of many neurons, which allows one to completely characterize their training and generalization behavior. No such general understanding…

Quantum Physics · Physics 2025-02-07 Eric R. Anschuetz

Despite classical statistical theory predicting severe overfitting, modern massively overparameterized neural networks still generalize well. This unexpected property is attributed to the network's so-called implicit bias, which describes…

Machine Learning · Computer Science 2025-03-14 Justin Sahs , Ryan Pyle , Fabio Anselmi , Ankit Patel

It is a common assumption that the activation of different layers in neural networks follow Gaussian distribution. This distribution can be transformed using normalization techniques, such as batch-normalization, increasing convergence…

Machine Learning · Computer Science 2020-10-19 Andras Horvath , Jalal Al-afandi

Recent theoretical work has demonstrated that deep neural networks have superior performance over shallow networks, but their training is more difficult, e.g., they suffer from the vanishing gradient problem. This problem can be typically…

Machine Learning · Statistics 2021-11-03 Lu Lu , Yanhui Su , George Em Karniadakis

In this paper, we are concerned with the generalization performance of non-parametric estimation for pairwise learning. Most of the existing work requires the hypothesis space to be convex or a VC-class, and the loss to be convex. However,…

Machine Learning · Statistics 2026-02-12 Junyu Zhou , Shuo Huang , Han Feng , Puyu Wang , Ding-Xuan Zhou

We establish a margin based data dependent generalization error bound for a general family of deep neural networks in terms of the depth and width, as well as the Jacobian of the networks. Through introducing a new characterization of the…

Machine Learning · Computer Science 2019-07-05 Xingguo Li , Junwei Lu , Zhaoran Wang , Jarvis Haupt , Tuo Zhao

The generalization mystery of overparametrized deep nets has motivated efforts to understand how gradient descent (GD) converges to low-loss solutions that generalize well. Real-life neural networks are initialized from small random values…

Machine Learning · Computer Science 2021-11-10 Kaifeng Lyu , Zhiyuan Li , Runzhe Wang , Sanjeev Arora

We consider a one-hidden-layer leaky ReLU network of arbitrary width trained by stochastic gradient descent (SGD) following an arbitrary initialization. We prove that SGD produces neural networks that have classification accuracy…

Machine Learning · Computer Science 2021-02-16 Spencer Frei , Yuan Cao , Quanquan Gu