中文
相关论文

相关论文: An in-depth look at approximation via deep and nar…

200 篇论文

We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer…

机器学习 · 计算机科学 2017-11-22 Kenji Kawaguchi , Bo Xie , Vikas Verma , Le Song

This paper extends the proof of density of neural networks in the space of continuous (or even measurable) functions on Euclidean spaces to functions on compact sets of probability measures. By doing so the work parallels a more then a…

机器学习 · 计算机科学 2019-06-04 Tomas Pevny , Vojtech Kovarik

This study explores the number of neurons required for a Rectified Linear Unit (ReLU) neural network to approximate multivariate monomials. We establish an exponential lower bound on the complexity of any shallow network approximating the…

机器学习 · 计算机科学 2023-05-17 Itai Shapira

Approximation and learning of classifiers of large data sets by neural networks in terms of high-dimensional geometry and statistical learning theory are investigated. The influence of the VC dimension of sets of input-output functions of…

机器学习 · 统计学 2025-11-18 Vera Kurkova , Marcello Sanguineti

This paper studies the universal approximation property of deep neural networks for representing probability distributions. Given a target distribution $\pi$ and a source distribution $p_z$ both defined on $\mathbb{R}^d$, we prove under…

机器学习 · 计算机科学 2020-11-17 Yulong Lu , Jianfeng Lu

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…

机器学习 · 计算机科学 2024-07-08 Jonatan Vallin , Karl Larsson , Mats G. Larson

This paper studies the approximation capacity of neural networks with an arbitrary activation function and with norm constraint on the weights. Upper and lower bounds on the approximation error of these networks are computed for smooth…

数值分析 · 数学 2025-12-24 Francesco Paolo Maiale , Anastasiia Trofimova , Arturo De Marinis

This work addresses two fundamental limitations in neural network approximation theory. We demonstrate that a three-dimensional network architecture enables a significantly more efficient representation of sawtooth functions, which serves…

机器学习 · 统计学 2026-03-13 ZeYu Li , FengLei Fan , TieYong Zeng

Recent results in nonparametric regression show that deep learning, i.e., neural network estimates with many hidden layers, are able to circumvent the so-called curse of dimensionality in case that suitable restrictions on the structure of…

机器学习 · 统计学 2020-09-30 Michael Kohler , Sophie Langer

We define a neural network in infinite dimensional spaces for which we can show the universal approximation property. Indeed, we derive approximation results for continuous functions from a Fr\'echet space $\X$ into a Banach space $\Y$. The…

泛函分析 · 数学 2022-05-18 Fred Espen Benth , Nils Detering , Luca Galimberti

We discovered that the neural networks, especially the deep ReLU networks, demonstrate an `over-generalization' phenomenon. That is, the output values for the inputs that were not seen during training are mapped close to the output range…

机器学习 · 计算机科学 2024-10-23 Harsh Shrivastava

The celebrated universal approximation theorems for neural networks roughly state that any reasonable function can be arbitrarily well-approximated by a network whose parameters are appropriately chosen real numbers. This paper examines the…

机器学习 · 计算机科学 2023-03-17 C. Sinan Güntürk , Weilin Li

Training neural networks to be certifiably robust is critical to ensure their safety against adversarial attacks. However, it is currently very difficult to train a neural network that is both accurate and certifiably robust. In this work…

机器学习 · 计算机科学 2020-01-16 Maximilian Baader , Matthew Mirman , Martin Vechev

This work studies approximation based on single-hidden-layer feedforward and recurrent neural networks with randomly generated internal weights. These methods, in which only the last layer of weights and a few hyperparameters are optimized,…

概率论 · 数学 2021-02-17 Lukas Gonon , Lyudmila Grigoryeva , Juan-Pablo Ortega

We show that deep sparse ReLU networks with ternary weights and deep ReLU networks with binary weights can approximate $\beta$-H\"older functions on $[0,1]^d$. Also, for any interval $[a,b)\subset\mathbb{R}$, continuous functions on…

神经与进化计算 · 计算机科学 2022-07-11 Aleksandr Beknazaryan

We derive upper bounds on the complexity of ReLU neural networks approximating the solution maps of parametric partial differential equations. In particular, without any knowledge of its concrete shape, we use the inherent…

数值分析 · 数学 2020-05-15 Gitta Kutyniok , Philipp Petersen , Mones Raslan , Reinhold Schneider

The realization function of a shallow ReLU network is a continuous and piecewise affine function $f:\mathbb R^d\to \mathbb R$, where the domain $\mathbb R^{d}$ is partitioned by a set of $n$ hyperplanes into cells on which $f$ is affine. We…

机器学习 · 计算机科学 2021-08-13 S. Dereich , S. Kassing

The purpose of the present paper is to study the computation complexity of deep ReLU neural networks to approximate functions in H\"older-Nikol'skii spaces of mixed smoothness $H_\infty^\alpha(\mathbb{I}^d)$ on the unit cube…

数值分析 · 数学 2021-03-02 Dinh Dũng , Van Kien Nguyen , Mai Xuan Thao

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…

机器学习 · 计算机科学 2025-04-01 Devon Jarvis , Richard Klein , Benjamin Rosman , Andrew M. Saxe

When studying the expressive power of neural networks, a main challenge is to understand how the size and depth of the network affect its ability to approximate real functions. However, not all functions are interesting from a practical…

机器学习 · 计算机科学 2021-06-30 Gal Vardi , Daniel Reichman , Toniann Pitassi , Ohad Shamir
‹ 上一页 1 8 9 10 下一页 ›