English
Related papers

Related papers: Universal Approximation with Deep Narrow Networks

200 papers

This paper focuses on establishing $L^2$ approximation properties for deep ReLU convolutional neural networks (CNNs) in two-dimensional space. The analysis is based on a decomposition theorem for convolutional kernels with a large spatial…

Machine Learning · Computer Science 2022-07-04 Juncai He , Lin Li , Jinchao Xu

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

A new network with super approximation power is introduced. This network is built with Floor ($\lfloor x\rfloor$) or ReLU ($\max\{0,x\}$) activation function in each neuron and hence we call such networks Floor-ReLU networks. For any…

Machine Learning · Computer Science 2021-03-30 Zuowei Shen , Haizhao Yang , Shijun Zhang

Constructing neural networks for function approximation is a classical and longstanding topic in approximation theory. In this paper, we aim at constructing deep neural networks (deep nets for short) with three hidden layers to approximate…

Information Theory · Computer Science 2020-01-14 Xia Liu

We study the size of a neural network needed to approximate the maximum function over $d$ inputs, in the most basic setting of approximating with respect to the $L_2$ norm, for continuous distributions, for a network that uses ReLU…

Machine Learning · Computer Science 2023-11-08 Itay Safran , Daniel Reichman , Paul Valiant

We make the case for neural network objects and extend an already existing neural network calculus explained in detail in Chapter 2 on \cite{bigbook}. Our aim will be to show that, yes, indeed, it makes sense to talk about neural network…

Machine Learning · Computer Science 2024-02-05 Shakil Rafi , Joshua Lee Padgett , Ukash Nakarmi

In this paper, we leverage a recent deep kernel representer theorem to connect kernel based learning and (deep) neural networks in order to understand their interplay. In particular, we show that the use of special types of kernels yields…

Machine Learning · Computer Science 2025-09-19 Tizian Wenzel , Gabriele Santin , Bernard Haasdonk

Neural networks are widely used to approximate unknown functions in control. A common neural network architecture uses a single hidden layer (i.e. a shallow network), in which the input parameters are fixed in advance and only the output…

Machine Learning · Computer Science 2024-10-08 Andrew Lamperski , Siddharth Salapaka

With the increasing popularity of non-convex deep models, developing a unifying theory for studying the optimization problems that arise from training these models becomes very significant. Toward this end, we present in this paper a…

Optimization and Control · Mathematics 2023-08-07 Maher Nouiehed , Meisam Razaviyayn

Classical results in neural network approximation theory show how arbitrary continuous functions can be approximated by networks with a single hidden layer, under mild assumptions on the activation function. However, the classical theory…

Optimization and Control · Mathematics 2023-04-06 Tyler Lekang , Andrew Lamperski

Neural networks are complex functions of both their inputs and parameters. Much prior work in deep learning theory analyzes the distribution of network outputs at a fixed a set of inputs (e.g. a training dataset) over random initializations…

Disordered Systems and Neural Networks · Physics 2025-04-08 Mike Winer , Boris Hanin

Based on the tree architecture, the objective of this paper is to design deep neural networks with two or more hidden layers (called deep nets) for realization of radial functions so as to enable rotational invariance for near-optimal…

Machine Learning · Computer Science 2019-04-04 Charles K. Chui , Shao-Bo Lin , Ding-Xuan Zhou

We demonstrate that a very deep ResNet with stacked modules with one neuron per hidden layer and ReLU activation functions can uniformly approximate any Lebesgue integrable function in $d$ dimensions, i.e. $\ell_1(\mathbb{R}^d)$. Because of…

Machine Learning · Computer Science 2018-07-05 Hongzhou Lin , Stefanie Jegelka

This paper establishes the (nearly) optimal approximation error characterization of deep rectified linear unit (ReLU) networks for smooth functions in terms of both width and depth simultaneously. To that end, we first prove that…

Machine Learning · Computer Science 2021-11-03 Jianfeng Lu , Zuowei Shen , Haizhao Yang , Shijun Zhang

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

We examine the closedness of sets of realized neural networks of a fixed architecture in Sobolev spaces. For an exactly $m$-times differentiable activation function $\rho$, we construct a sequence of neural networks $(\Phi_n)_{n \in…

Machine Learning · Statistics 2021-01-29 Scott Mahan , Emily King , Alex Cloninger

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

Although for neural networks with locally Lipschitz continuous activation functions the classical derivative exists almost everywhere, the standard chain rule is in general not applicable. We will consider a way of introducing a derivative…

Machine Learning · Computer Science 2020-11-12 Julius Berner , Dennis Elbrächter , Philipp Grohs , Arnulf Jentzen

Deep Operator Networks (DeepONets) provide a branch-trunk neural architecture for approximating nonlinear operators acting between function spaces. In the classical operator approximation framework, the input is a function $u\in C(K_1)$…

Machine Learning · Computer Science 2026-03-13 Vugar Ismailov

Does over-parameterization eliminate sub-optimal local minima for neural networks? An affirmative answer was given by a classical result in [59] for 1-hidden-layer wide neural networks. A few recent works have extended the setting to…

Machine Learning · Computer Science 2020-11-17 Tian Ding , Dawei Li , Ruoyu Sun
‹ Prev 1 8 9 10 Next ›