English
Related papers

Related papers: Just One Layer Norm Guarantees Stable Extrapolatio…

200 papers

In Convolutional Neural Network (CNN) based image processing, most studies propose networks that are optimized to single-level (or single-objective); thus, they underperform on other levels and must be retrained for delivery of optimal…

Computer Vision and Pattern Recognition · Computer Science 2020-10-07 Hyeongmin Lee , Taeoh Kim , Hanbin Son , Sangwook Baek , Minsu Cheon , Sangyoun Lee

Yang (2020a) recently showed that the Neural Tangent Kernel (NTK) at initialization has an infinite-width limit for a large class of architectures including modern staples such as ResNet and Transformers. However, their analysis does not…

Machine Learning · Computer Science 2021-05-11 Greg Yang , Etai Littwin

We prove the converse of the universal approximation theorem, i.e. a neural network (NN) encoding theorem which shows that for every stably converged NN of continuous activation functions, its weight matrix actually encodes a continuous…

Machine Learning · Computer Science 2023-09-13 Ng Shyh-Chang , A-Li Luo , Bo Qiu

Deep neural networks' remarkable ability to correctly fit training data when optimized by gradient-based algorithms is yet to be fully understood. Recent theoretical results explain the convergence for ReLU networks that are wider than…

Machine Learning · Computer Science 2021-02-09 Asaf Noy , Yi Xu , Yonathan Aflalo , Lihi Zelnik-Manor , Rong Jin

Understanding deep neural networks (DNNs) is a key challenge in the theory of machine learning, with potential applications to the many fields where DNNs have been successfully used. This article presents a scaling limit for a DNN being…

Statistics Theory · Mathematics 2019-06-04 Dyego Araújo , Roberto I. Oliveira , Daniel Yukimura

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

Machine Learning · Computer Science 2018-02-06 Amir Rosenfeld , John K. Tsotsos

The Neural Tangent Kernel (NTK) framework has provided deep insights into the training dynamics of neural networks under gradient flow. However, it relies on the assumption that the network is differentiable with respect to its parameters,…

Machine Learning · Computer Science 2025-09-17 Sriram Nagaraj , Vishakh Hari

Neural networks are known to develop latent representations that are $aligned$, namely structurally similar across networks trained with different architectures, training protocols, or training datasets. We study this phenomenon in a…

Machine Learning · Statistics 2026-05-27 Ali Hussaini Umar , Alessandro Laio

Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their static structure limits their adaptability in ever-changing environments. This…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Yunjie Zhu , Yunhao Chen

In the present paper, we consider one-hidden layer ANNs with a feedforward architecture, also referred to as shallow or two-layer networks, so that the structure is determined by the number and types of neurons. The determination of the…

An interesting observation in artificial neural networks is their favorable generalization error despite typically being extremely overparameterized. It is well known that the classical statistical learning methods often result in vacuous…

Machine Learning · Computer Science 2021-10-12 Sattar Vakili , Michael Bromberg , Jezabel Garcia , Da-shan Shiu , Alberto Bernacchia

Neural models combining representation learning and reasoning in an end-to-end trainable manner are receiving increasing interest. However, their use is severely limited by their computational complexity, which renders them unusable on real…

Artificial Intelligence · Computer Science 2018-07-24 Pasquale Minervini , Matko Bosnjak , Tim Rocktäschel , Sebastian Riedel

Deep neural networks (DNNs) defy the classical bias-variance trade-off: adding parameters to a DNN that interpolates its training data will typically improve its generalization performance. Explaining the mechanism behind this ``benign…

Machine Learning · Statistics 2023-05-02 Diego Doimo , Aldo Glielmo , Sebastian Goldt , Alessandro Laio

In this paper, we study the generalization performance of min $\ell_2$-norm overfitting solutions for the neural tangent kernel (NTK) model of a two-layer neural network with ReLU activation that has no bias term. We show that, depending on…

Machine Learning · Computer Science 2023-03-09 Peizhong Ju , Xiaojun Lin , Ness B. Shroff

Fully-connected deep neural networks with weights initialized from independent Gaussian distributions can be tuned to criticality, which prevents the exponential growth or decay of signals propagating through the network. However, such…

Machine Learning · Computer Science 2024-06-13 Hannah Day , Yonatan Kahn , Daniel A. Roberts

We study how neural networks compress uninformative input space in models where data lie in $d$ dimensions, but whose label only vary within a linear manifold of dimension $d_\parallel < d$. We show that for a one-hidden layer network…

Machine Learning · Computer Science 2021-05-07 Jonas Paccolat , Leonardo Petrini , Mario Geiger , Kevin Tyloo , Matthieu Wyart

Convolutional Neural Networks (CNNs) excel at extracting local features hierarchically, but their performance in capturing complex correlations hinges heavily on deep architectures, which are usually computationally demanding and difficult…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Chia-Wei Hsing , Wei-Lin Tu

We introduce the concept of scalable neural network kernels (SNNKs), the replacements of regular feedforward layers (FFLs), capable of approximating the latter, but with favorable computational properties. SNNKs effectively disentangle the…

Machine Learning · Computer Science 2024-03-07 Arijit Sehanobish , Krzysztof Choromanski , Yunfan Zhao , Avinava Dubey , Valerii Likhosherstov

When optimizing convolutional neural networks (CNN) for a specific image-based task, specialists commonly overshoot the number of convolutional layers in their designs. By implication, these CNNs are unnecessarily resource intensive to…

Machine Learning · Computer Science 2022-06-23 Mats L. Richter , Julius Schöning , Anna Wiedenroth , Ulf Krumnack

Graph neural networks (GNNs) provide state-of-the-art results in a wide variety of tasks which typically involve predicting features at the vertices of a graph. They are built from layers of graph convolutions which serve as a powerful…

Machine Learning · Statistics 2024-11-08 Mauricio Velasco , Kaiying O'Hare , Bernardo Rychtenberg , Soledad Villar