Cover Image

Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Li'ang, Duan, Yifei, Ji, Guanghua, Cai, Yongqiang
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Numerical Analysis 68T07, 65P99, 65Z05, 41A65
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systems
by: Duan, Yifei, et al.
Published: (2022)

Achieving Universal Approximation and Universal Interpolation via Nonlinearity of Control Families
by: Cai, Yongqiang, et al.
Published: (2025)

A Minimal Control Family of Dynamical Systems for Universal Approximation
by: Duan, Yifei, et al.
Published: (2023)

Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver
by: Sittoni, Pietro, et al.
Published: (2026)

Equidistribution-based training of Free Knot Splines and ReLU Neural Networks
by: Appella, Simone, et al.
Published: (2024)

How Can Deep Neural Networks Fail Even With Global Optima?
by: Guan, Qingguang
Published: (2024)

PODNO: Proper Orthogonal Decomposition Neural Operators
by: Cheng, Zilan, et al.
Published: (2025)

Neural Network Element Method for Partial Differential Equations
by: Wang, Yifan, et al.
Published: (2025)

Regularity Analysis and Tensor Neural Network Methods for Quasiperiodic Elliptic Equations
by: Ren, Jingze, et al.
Published: (2026)

Solving High Dimensional Partial Differential Equations Using Tensor Neural Network and A Posteriori Error Estimators
by: Wang, Yifan, et al.
Published: (2023)

Derivative-Informed Fourier Neural Operator: Universal Approximation and Applications to PDE-Constrained Optimization
by: Yao, Boyuan, et al.
Published: (2025)

Neural Ordinary Differential Equations for Model Order Reduction of Stiff Systems
by: Caldana, Matteo, et al.
Published: (2024)

Universal Approximation of Dynamical Systems by Semi-Autonomous Neural ODEs and Applications
by: Li, Ziqian, et al.
Published: (2024)

Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations
by: Chen, Shuang, et al.
Published: (2026)

A Structure-Preserving Framework for Solving Parabolic Partial Differential Equations with Neural Networks
by: Chen, Gaohang, et al.
Published: (2025)

Enhancing Future Prediction of Linear and Nonlinear Reduced-Order Models for Transport-Dominated Problems Using Lagrangian Data
by: Li, Meng, et al.
Published: (2026)

Sensitivity of low-rank matrix recovery
by: Breiding, Paul, et al.
Published: (2021)

Data Completion for Electrical Impedance Tomography by Conditional Diffusion Models
by: Chen, Ke, et al.
Published: (2026)

The lowest-order Neural Approximated Virtual Element Method on polygonal elements
by: Berrone, Stefano, et al.
Published: (2024)

On the algorithmic construction of deep ReLU networks
by: Huybrechs, Daan
Published: (2025)

Neural Approximate Inverse Preconditioners
by: Xu, Tianshi, et al.
Published: (2025)

Multiscale Neural Networks for Approximating Green's Functions
by: Hao, Wenrui, et al.
Published: (2024)

High order positivity-preserving numerical methods for a non-local photochemical model
by: Pezzella, Mario
Published: (2025)

Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization
by: Park, Youngjae, et al.
Published: (2026)

Universal approximation property of ODENet and ResNet with a single activation function
by: Kimura, Masato, et al.
Published: (2024)

Error bounds for Physics Informed Neural Networks in Nonlinear Schrödinger equations placed on unbounded domains
by: Alejo, Miguel Á., et al.
Published: (2024)

S$^2$GPT-PINNs: Sparse and Small models for PDEs
by: Ji, Yajie, et al.
Published: (2025)

Deep asymptotic expansion method for solving singularly perturbed time-dependent reaction-advection-diffusion equations
by: Zhu, Qiao, et al.
Published: (2025)

The Neural Approximated Virtual Element Method for Elasticity Problems
by: Berrone, Stefano, et al.
Published: (2025)

A Modular Deep Learning-based Approach for Diffuse Optical Tomography Reconstruction
by: Benfenati, Alessandro, et al.
Published: (2024)

Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for space-time solutions of semilinear partial differential equations
by: Ackermann, Julia, et al.
Published: (2024)

All Equalities Are Equal, but Some Are More Equal Than Others: The Effect of Implementation Aliasing on the Numerical Solution to Conservation Equations
by: Trojak, Will, et al.
Published: (2019)

Adaptive Randomized Neural Networks with Locally Activation Function: Theory and Algorithm for Solving PDEs
by: Bi, Ran, et al.
Published: (2026)

SUPN: Shallow Universal Polynomial Networks
by: Morrow, Zachary, et al.
Published: (2025)

Enforcing boundary conditions for physics-informed neural operators
by: Göschel, Niklas, et al.
Published: (2025)

Data-driven computation for periodic stochastic differential equations
by: Li, Yao, et al.
Published: (2025)

Physics-Informed Neural Networks: A Didactic Derivation of the Complete Training Cycle
by: Tahimi, Abdeladhim
Published: (2026)

Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense
by: Ackermann, Julia, et al.
Published: (2023)

Improving Matrix Exponential for Generative AI Flows: A Taylor-Based Approach Beyond Paterson--Stockmeyer
by: Sastre, Jorge, et al.
Published: (2025)

A Low Rank Neural Representation of Entropy Solutions
by: Rim, Donsub, et al.
Published: (2024)