Analytic function approximation by path norm regularized deep networks

We show that neural networks with absolute value activation function and with the path norm, the depth, the width and the network weights having logarithmic dependence on $1/\varepsilon$ can $\varepsilon$-approximate functions that are analytic on certain regions of $\mathbb{C}^d$.

stat.ML cs.LG Neural Networks and Applications Model Reduction and Neural Networks Stochastic Gradient Optimization Techniques Computer Science Mathematics Medicine

View graph Source

Paper

Similar papers

Analytic Function Approximation by Path-Norm-Regularized Deep Neural NetworksAleksandr Beknazaryan2022 · Entropy In Library

Analytic Regularity and Approximation Limits of Coefficient-Constrained Shallow NetworksJean-Gabriel Attali2026 · HAL (Le Centre pour la Communication Scientifique Directe) In Library

Approximation bounds for norm constrained deep neural networksFrancesco Paolo Maiale, Anastasiia Trofimova, Arturo De Marinis2025 · arXiv (Cornell University) · 0 citations In Library

Exponential Convergence of the Deep Neural Network Approximation for Analytic FunctionsW. E, Qingcan Wang2018 · Science China Mathematics · 112 citations In Library

Deep Learning in High Dimension: Neural Network Approximation of Analytic Functions in $L^2(\mathbb{R}^d,γ_d)$C. Schwab, J. Zech2021 · arXiv.org · 6 citations In Library

Simultaneous neural network approximation for smooth functionsS. Hon, Haizhao Yang2021 · Neural Networks · 22 citations In Library

Universal approximation results for neural networks with non-polynomial activation function over non-compact domainsAriel Neufeld, Philipp Schmocker2024 · arXiv (Cornell University) · 10 citations In Library

Optimal Approximation Complexity of High-Dimensional Functions with Neural NetworksVincent P. H. Goverse, Jad Hamdan, Jared Tanner2023 · arXiv.org · 0 citations In Library

Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activationsDenis Belomestny, Alexey Naumov, Nikita Puchkin et al.2022 · arXiv (Cornell University) · 42 citations In Library

Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and WidthYanming Lai, Defeng Sun, Yang Wang2026 · 0 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal