English
Related papers

Related papers: Width is Less Important than Depth in ReLU Neural …

200 papers

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

The massive computational costs of scaling modern deep learning architectures have driven the widespread use of parameter-efficient low-rank structures, such as LoRA and low-rank factorization. However, theoretical guarantees for their…

Machine Learning · Computer Science 2026-05-08 Ying Chen , Aoxi Li , Jihun Kim , Javad Lavaei

We analyze the optimization landscapes of deep learning with wide networks. We highlight the importance of constraints for such networks and show that constraint -- as well as unconstraint -- empirical-risk minimization over such networks…

Machine Learning · Computer Science 2021-01-14 Johannes Lederer

The Strong Lottery Ticket Hypothesis (SLTH) posits that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a target function at initialization without training, suggesting that pruning alone is…

Machine Learning · Computer Science 2026-03-05 Davide Ferre' , Frédéric Giroire , Frederik Mallmann-Trenn , Emanuele Natale

We study the expressivity of ReLU neural networks in the setting of a binary classification problem from a topological perspective. Recently, empirical studies showed that neural networks operate by changing topology, transforming a…

Machine Learning · Computer Science 2024-06-12 Ekin Ergen , Moritz Grillo

In the desire to quantify the success of neural networks in deep learning and other applications, there is a great interest in understanding which functions are efficiently approximated by the outputs of neural networks. By now, there…

In practice, multi-task learning (through learning features shared among tasks) is an essential property of deep neural networks (NNs). While infinite-width limits of NNs can provide good intuition for their generalization behavior, the…

Machine Learning · Computer Science 2022-10-21 Jakob Heiss , Josef Teichmann , Hanna Wutte

Network pruning reduces the computation costs of an over-parameterized network without performance damage. Prevailing pruning algorithms pre-define the width and depth of the pruned networks, and then transfer parameters from the unpruned…

Computer Vision and Pattern Recognition · Computer Science 2019-10-17 Xuanyi Dong , Yi Yang

There is some theoretical evidence that deep neural networks with multiple hidden layers have a potential for more efficient representation of multidimensional mappings than shallow networks with a single hidden layer. The question is…

Machine Learning · Computer Science 2019-10-08 Bernhard Bermeitinger , Tomas Hrycej , Siegfried Handschuh

The geometric structure of an optimization landscape is argued to be fundamentally important to support the success of deep neural network learning. A direct computation of the landscape beyond two layers is hard. Therefore, to capture the…

Machine Learning · Computer Science 2021-10-04 Wenxuan Zou , Haiping Huang

Deep neural networks are powerful tools to model observations over time with non-linear patterns. Despite the widespread use of neural networks in such settings, most theoretical developments of deep neural networks are under the assumption…

Machine Learning · Statistics 2022-10-24 Mingliang Ma , Abolfazl Safikhani

We prove bounds for the approximation and estimation of certain binary classification functions using ReLU neural networks. Our estimation bounds provide a priori performance guarantees for empirical risk minimization using networks of a…

Functional Analysis · Mathematics 2022-03-11 Andrei Caragea , Philipp Petersen , Felix Voigtlaender

Redundancy in deep neural network (DNN) models has always been one of their most intriguing and important properties. DNNs have been shown to overparameterize, or extract a lot of redundant features. In this work, we explore the impact of…

Machine Learning · Computer Science 2019-01-31 Babajide O. Ayinde , Tamer Inanc , Jacek M. Zurada

In this article we study high-dimensional approximation capacities of shallow and deep artificial neural networks (ANNs) with the rectified linear unit (ReLU) activation. In particular, it is a key contribution of this work to reveal that…

Numerical Analysis · Mathematics 2023-01-23 Lukas Gonon , Robin Graeber , Arnulf Jentzen

In spite of finite dimension ReLU neural networks being a consistent factor behind recent deep learning successes, a theory of feature learning in these models remains elusive. Currently, insightful theories still rely on assumptions…

Machine Learning · Computer Science 2025-04-01 Devon Jarvis , Richard Klein , Benjamin Rosman , Andrew M. Saxe

Recent works have shown that gradient descent can find a global minimum for over-parameterized neural networks where the widths of all the hidden layers scale polynomially with $N$ ($N$ being the number of training samples). In this paper,…

Machine Learning · Computer Science 2020-12-21 Quynh Nguyen , Marco Mondelli

We consider training over-parameterized two-layer neural networks with Rectified Linear Unit (ReLU) using gradient descent (GD) method. Inspired by a recent line of work, we study the evolutions of network prediction errors across GD…

Machine Learning · Computer Science 2019-09-04 Lili Su , Pengkun Yang

Deep neural networks are highly expressive machine learning models with the ability to interpolate arbitrary datasets. Deep nets are typically optimized via first-order methods and the optimization process crucially depends on the…

Machine Learning · Statistics 2019-11-12 Talha Cihad Gulcu

Two networks are equivalent if they produce the same output for any given input. In this paper, we study the possibility of transforming a deep neural network to another network with a different number of units or layers, which can be…

Machine Learning · Computer Science 2019-05-29 Abhinav Kumar , Thiago Serra , Srikumar Ramalingam

Why do deep neural networks (DNNs) benefit from very high dimensional parameter spaces? Their huge parameter complexities vs stunning performance in practice is all the more intriguing and not explainable using the standard theory of model…

Machine Learning · Computer Science 2025-06-12 Ke Sun , Frank Nielsen