中文
相关论文

相关论文: Triangulating PL functions and the existence of ef…

200 篇论文

Given a piecewise linear (PL) function $p$ defined on an open subset of $\R^n$, one may construct by elementary means a unique polyhedron with multiplicities $\D(p)$ in the cotangent bundle $\R^n\times \R^{n*}$ representing the graph of the…

微分几何 · 数学 2013-06-20 Joseph H. G. Fu , Ryan C. Scott

We contribute to a better understanding of the class of functions that can be represented by a neural network with ReLU activations and a given architecture. Using techniques from mixed-integer optimization, polyhedral theory, and tropical…

机器学习 · 计算机科学 2024-07-18 Christoph Hertrich , Amitabh Basu , Marco Di Summa , Martin Skutella

It is shown that any continuous piecewise affine (CPA) function $\mathbb{R}^2\to\mathbb{R}$ with $p$ pieces can be represented by a ReLU neural network with two hidden layers and $O(p)$ neurons. Unlike prior work, which focused on convex…

机器学习 · 计算机科学 2025-03-18 Leo Zanotti

In this paper we investigate the family of functions representable by deep neural networks (DNN) with rectified linear units (ReLU). We give an algorithm to train a ReLU DNN with one hidden layer to *global optimality* with runtime…

机器学习 · 计算机科学 2018-03-01 Raman Arora , Amitabh Basu , Poorya Mianjy , Anirbit Mukherjee

This paper analyzes representations of continuous piecewise linear functions with infinite width, finite cost shallow neural networks using the rectified linear unit (ReLU) as an activation function. Through its integral representation, a…

机器学习 · 计算机科学 2023-09-26 Sarah McCarty

We point out that (continuous or discontinuous) piecewise linear functions on a convex polytope mesh can be represented by two-hidden-layer ReLU neural networks in a weak sense. In addition, the numbers of neurons of the two hidden layers…

数值分析 · 数学 2026-01-06 Pengzhan Jin

This paper studies the approximation property of ReLU neural networks (NNs) to piecewise constant functions with unknown interfaces in bounded regions in $\mathbb{R}^d$. Under the assumption that the discontinuity interface $\Gamma$ may be…

泛函分析 · 数学 2024-10-23 Zhiqiang Cai , Junpyo Choi , Min Liu

In recent years, functional neural networks have been proposed and studied in order to approximate nonlinear continuous functionals defined on $L^p([-1, 1]^s)$ for integers $s\ge1$ and $1\le p<\infty$. However, their theoretical properties…

机器学习 · 统计学 2023-04-11 Linhao Song , Jun Fan , Di-Rong Chen , Ding-Xuan Zhou

We apply a generalized piecewise-linear (PL) version of Morse theory due to Grunert-Kuhnel-Rote to define and study new local and global notions of topological complexity for fully-connected feedforward ReLU neural network functions, F: R^n…

代数拓扑 · 数学 2024-04-03 J. Elisenda Grigsby , Kathryn Lindsey , Marissa Masden

One common function class in machine learning is the class of ReLU neural networks. ReLU neural networks induce a piecewise linear decomposition of their input space called the canonical polyhedral complex. It has previously been…

代数拓扑 · 数学 2025-01-24 Robyn Brooks , Marissa Masden

Neural networks and rational functions efficiently approximate each other. In more detail, it is shown here that for any ReLU network, there exists a rational function of degree $O(\text{polylog}(1/\epsilon))$ which is $\epsilon$-close, and…

机器学习 · 计算机科学 2017-06-13 Matus Telgarsky

We study the problem of approximating compactly-supported integrable functions while implementing their support set using feedforward neural networks. Our first main result transcribes this "structured" approximation problem into a…

机器学习 · 计算机科学 2022-08-02 Anastasis Kratsios , Behnoosh Zamanlooy

A ReLU neural network leads to a finite polyhedral decomposition of input space and a corresponding finite dual graph. We show that while this dual graph is a coarse quantization of input space, it is sufficiently robust that it can be…

代数拓扑 · 数学 2023-07-03 Yajing Liu , Christina M Cole , Chris Peterson , Michael Kirby

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

In this study, we establish that deep neural networks employing ReLU and ReLU$^2$ activation functions can effectively represent Lagrange finite element functions of any order on various simplicial meshes in arbitrary dimensions. We…

数值分析 · 数学 2024-01-15 Juncai He , Jinchao Xu

In this paper, we investigate the relationship between deep neural networks (DNN) with rectified linear unit (ReLU) function as the activation function and continuous piecewise linear (CPWL) functions, especially CPWL functions from the…

数值分析 · 数学 2020-06-02 Juncai He , Lin Li , Jinchao Xu , Chunyue Zheng

A neural network consisting of piecewise affine building blocks, such as fully-connected layers and ReLU activations, is itself a piecewise affine function supported on a polyhedral complex. This complex has been previously studied to…

机器学习 · 计算机科学 2023-06-13 Arturs Berzins

The foundations of deep learning are supported by the seemingly opposing perspectives of approximation or learning theory. The former advocates for large/expressive models that need not generalize, while the latter considers classes that…

机器学习 · 计算机科学 2025-06-27 Ruiyang Hong , Anastasis Kratsios

In a function approximation with a neural network, an input dataset is mapped to an output index by optimizing the parameters of each hidden-layer unit. For a unary function, we present constraints on the parameters and its second…

机器学习 · 统计学 2020-06-22 Masayo Inoue , Mana Futamura , Hirokazu Ninomiya

In this article we identify a general class of high-dimensional continuous functions that can be approximated by deep neural networks (DNNs) with the rectified linear unit (ReLU) activation without the curse of dimensionality. In other…

数值分析 · 数学 2023-04-13 Adrian Riekert
‹ 上一页 1 2 3 10 下一页 ›