English
Related papers

Related papers: Some Theoretical Results on Layerwise Effective Di…

200 papers

We study the problem of symmetric positive semi-definite low-rank matrix completion (MC) with deterministic entry-dependent sampling. In particular, we consider rectified linear unit (ReLU) sampling, where only positive entries are…

Machine Learning · Computer Science 2024-06-11 Huikang Liu , Peng Wang , Longxiu Huang , Qing Qu , Laura Balzano

In this article we study fully-connected feedforward deep ReLU ANNs with an arbitrarily large number of hidden layers and we prove convergence of the risk of the GD optimization method with random initializations in the training of such…

Optimization and Control · Mathematics 2022-07-14 Arnulf Jentzen , Adrian Riekert

We study the least-square regression problem with a two-layer fully-connected neural network, with ReLU activation function, trained by gradient flow. Our first result is a generalization result, that requires no assumptions on the…

Machine Learning · Computer Science 2024-10-10 Junhyung Park , Patrick Bloebaum , Shiva Prasad Kasiviswanathan

We introduce the "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher classification accuracies. Like rectified linear units (ReLUs), leaky ReLUs (LReLUs) and parametrized ReLUs (PReLUs), ELUs…

Machine Learning · Computer Science 2016-02-23 Djork-Arné Clevert , Thomas Unterthiner , Sepp Hochreiter

The expressivity of neural networks as a function of their depth, width and type of activation units has been an important question in deep learning theory. Recently, depth separation results for ReLU networks were obtained via a new…

Machine Learning · Computer Science 2020-07-21 Vaggos Chatziafratis , Sai Ganesh Nagarajan , Ioannis Panageas

This paper is devoted to studying the optimal expressive power of ReLU deep neural networks (DNNs) and its application in approximation via the Kolmogorov Superposition Theorem. We first constructively prove that any continuous piecewise…

Machine Learning · Computer Science 2023-08-11 Juncai He

The choice of activation function fundamentally shapes the representational capacity and parameter efficiency of deep neural networks, yet most widely used activations lack rigorous theoretical guarantees on these properties. We provide a…

Machine Learning · Computer Science 2026-05-14 Ibrahim Albool , Malak Gamal El-Din , Salma Elmalaki , Yasser Shoukry

A new loss function is proposed for neural networks on classification tasks which extends the hinge loss by assigning gradients to its critical points. We will show that for a linear classifier on linearly separable data with fixed step…

Machine Learning · Computer Science 2020-06-26 Justin Lizama

We develop a geometric approximation theory for deep feed-forward neural networks with ReLU activations. Given a $d$-dimensional hypersurface in $\mathbb{R}^{d+1}$ represented as the graph of a $C^2$-function $\phi$, we show that a deep…

Machine Learning · Computer Science 2024-07-08 Jonatan Vallin , Karl Larsson , Mats G. Larson

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

Recent findings suggest that consecutive layers of neural networks with the ReLU activation function \emph{fold} the input space during the learning process. While many works hint at this phenomenon, an approach to quantify the folding was…

Machine Learning · Computer Science 2025-03-12 Michal Lewandowski , Bernhard Heinzl , Raphael Pisoni , Bernhard A. Moser

We present a unified theoretical framework connecting the first property of Deep Neural Collapse (DNC1) to the emergence of implicit low-rank bias in nonlinear networks trained with $L^2$ weight decay regularization. Our main contributions…

Machine Learning · Computer Science 2026-02-12 Emanuele Zangrando , Piero Deidda , Simone Brugiapaglia , Nicola Guglielmi , Francesco Tudisco

In this article, we study approximation properties of the variation spaces corresponding to shallow neural networks with a variety of activation functions. We introduce two main tools for estimating the metric entropy, approximation rates,…

Machine Learning · Statistics 2024-02-26 Jonathan W. Siegel , Jinchao Xu

It is well-known that the parameterized family of functions representable by fully-connected feedforward neural networks with ReLU activation function is precisely the class of piecewise linear functions with finitely many pieces. It is…

Metric Geometry · Mathematics 2026-01-21 J. Elisenda Grigsby , Kathryn Lindsey , Robert Meyerhoff , Chenxi Wu

The tremendous success of deep neural networks has motivated the need to better understand the fundamental properties of these networks, but many of the theoretical results proposed have only been for shallow networks. In this paper, we…

Data Structures and Algorithms · Computer Science 2020-02-20 Rajesh Jayaram , David P. Woodruff , Qiuyi Zhang

Recent findings suggest that the consecutive layers of ReLU neural networks can be understood geometrically as space folding transformations of the input space, revealing patterns of self-similarity. In this paper, we present the first…

Machine Learning · Computer Science 2025-02-17 Michal Lewandowski , Hamid Eghbalzadeh , Bernhard Heinzl , Raphael Pisoni , Bernhard A. Moser

We present a fully constructive analysis of deep ReLU neural networks for classification and function approximation tasks. First, we prove that any dataset with $N$ distinct points in $\mathbb{R}^d$ and $M$ output classes can be exactly…

Machine Learning · Statistics 2025-06-25 Martín Hernández , Enrique Zuazua

Whereas recovery of the manifold from data is a well-studied topic, approximation rates for functions defined on manifolds are less known. In this work, we study a regression problem with inputs on a $d^*$-dimensional manifold that is…

Machine Learning · Statistics 2019-08-05 Johannes Schmidt-Hieber

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

We constructively prove that every deep ReLU network can be rewritten as a functionally identical three-layer network with weights valued in the extended reals. Based on this proof, we provide an algorithm that, given a deep ReLU network,…

Machine Learning · Computer Science 2023-06-22 Mattia Jacopo Villani , Nandi Schoots